Gwern.net - Newest

NYT and Vaping: How To Lie By Saying Only True Things

Gwern Branwen — Invalid Date

The 2019 EVALI outbreak was caused by illicit THC vapes adulterated with vitamin E acetate, but it became a public justification for restrictions on legal nicotine vaping.

This essay looks at a 2022 New York Times article about teenage vaping which juxtaposes synthetic nicotine, flavored vapes, Lizzie Burgess’s hospitalization, and nicotine addiction without ever quite saying that legal flavored nicotine vapes caused her lung injury.

Sentence by sentence, the article’s misleading effect comes from technically true phrasing: “vaping”, “vaping THC and nicotine”, “vaping-related lung injury”, and post-hoc narrative order.

The case is a useful example because the ground truth is clear, the article was high-profile and edited, and the manipulation is grammatical and selection rather than simple falsehoods.

The 2019 nicotine vaping moral panic was one of the more striking ones of our era, where illegal black-market THC marijuana vapes poisoned with vitamin E acetate that caused severe “EVALI” lung injuries were a major justification for unprecedented bans on legal nicotine vaping products. Despite no lab-verified instance of a nicotine product with the vitamin E acetate adulteration (only THC products), and nicotine vapes produced by large businesses which had sold countless billions of doses to millions of people beforehand, with no EVALI epidemic before (or since), and the phenomenon subsiding after lawsuits and prosecutions of vitamin E acetate sellers, it somehow became common knowledge that nicotine vapes were deadly.

How did this happen?

Media Coverage

One way it happened was via a conflation of THC and nicotine vaping, driven in part by inaccurate reporting by victims and by the difficulty of proving a negative—after all, any given case could have been due to nicotine vaping, somehow, how would one prove it wasn’t? This was then amplified by activists and journalists working together to selectively report and describe true facts.

I was particularly struck by an instance in the New York Times in March 2022, which paints a compelling picture of legal nicotine vapes causing severe lung problems in one young woman, Lizzie Burgess:

[The Lizzie Burgess excerpt]

This article appears to have been successful in persuading readers. In the NYT comment section (mirrored below in full), most comments agreed with the article, often going as far as to claim that “addict and kill people—including children”/“here they are exploiting a legal loophole to addict millions more young adults to their lethal products” or “Young people especially become easily addicted to the nicotine…The damage to their lungs resembles the worst pneumonia you can get and still be alive.” or “The purveyors of these drug delivery systems are killing our children with intent. They should all be thrown in jail, and the import of these products should be banned.” (The import of THC vapes contaminated with vitamin E acetate is, of course, already banned or adult ID required etc.) Indeed, only a single NYT commenter (who no one responded to) appeared to get it right in their reply a quarter down the comment section:

The illness described in the article was clearly caused by using an adulterated, illegal, THC-containing vaping product, not the nicotine-based e-cigarettes being criticized here. That should have been made clearer.

The article might have convinced me too if I hadn’t already known better.

I was perplexed why the NYT would lie like that, as the article clearly said repeatedly that nicotine vaping was to blame. I had thought that it was now uncontroversial and consensus that the moral panic had framed nicotine vaping (albeit unpopular to acknowledge now that the ‘issue-attention cycle’ had moved on and the activists gotten what they wanted). Was it just wrong, or had I misunderstood something? Perhaps I had skimmed over a smoking gun, like finally finding fatal levels of vitamin E acetate in lab testing of a Juul pod?

Rhetoric

So I went back to excerpt the article—and while rereading, realized that in every case I thought might be a lie, rereading showed it had been so carefully worded as to be technically correct and to simply be misleading.

After this, I was in awe of the rare artistry of the piece, which elevated it from merely misleading to a wonderful example of “bounded distrust” in journalism and how selective quotation and mere juxtaposition can lead astray the insufficiently skeptical reader.

It’s a great example because it is:

Ground-truth objective answer, known then, and even more clearly confirmed by years of followup:

EVALI was caused by THC products. There is no hard lab-tested evidence that any legal nicotine products, the subject of the article, caused EVALI.
Longform (~1,800 words) high-profile piece in one of the most prestigious newspapers in the world:

meaning that it passed editing and fact-checking
Purely textual/grammatical:

phrases like “vaping products” or “vaping THC and nicotine” are suspiciously worded and violate ordinary norms of writing to be specific and informative—if a young woman has been hospitalized by a nicotine vaping product, why not say just so? If vitamin E acetate had been found in legal nicotine vaping products, why not just name the test result and product specifically?
Unnecessary to the core of the article:

it would be possible to write this story without bringing in irrelevant THC-contaminated anecdotes or EVALI, by focusing on legitimate criticisms of nicotine vaping. (You could discuss teen access, flavor marketing, age checks, FDA jurisdiction, statutory drafting, the economics of disposable devices, and the adult harm-reduction case without ever mentioning EVALI which you know is not related to teen access to legal anything.)
Deliberate: the phrasing is so consistently and carefully done that the author almost certainly knew what they were doing—if they hadn’t, they would have slipped up at least once, and joined two sentences with a comma, or some other easy writing mistake which would have been incorrect.

I kept thinking about what a great example it was and that at some point I should fisk it. Finally, I did.

The article’s misleading chain of logic is synthetic nicotine → vaping flavors → “vaping-related lung injury” → Lizzie Burgess; and in an anecdote demonstrating this: “flavored vapes” → “vaping THC and using a device” → “vaping-related lung injury” → “nicotine addiction” → ban “flavored vapes”.

But nowhere does it say anything like:

Her lung injury was caused by legal flavored nicotine vapes.

It is always ‘vaping caused lung injury’ (true! vaping THC products did) or ‘vaping THC and nicotine’ (the ‘and’ does a lot of work there), or juxtaposition like ‘she was soon in the ICU…She’s struggled to end her nicotine addiction’.

It just carefully arranges the sequence of facts to encourage the ordinary causal inference of post hoc ergo propter hoc, downplaying or omitting the THC, while using supersets like ‘vaping’ or ‘vaping THC and nicotine’ so the article technically contains the relevant information (the informed reader would interpret this correctly as Lizzie Burgess having almost surely been hospitalized by the THC vaping, but the ordinary reader has already been led down the wrong path—and confirmation bias does the rest).

It serves as a good exercise for the reader: how do you handle science journalism like this, where the author is not careless or egregiously lying, but where the author appears to know exactly where the line is and never quite crosses it? Or readers who ask only, “is each sentence technically true and lets me believe what I want to believe?” Would you have noticed the suspiciously specific wording, or the omission of how it never quite says, despite its length, a simple statement like “nicotine vapes caused EVALI”? Or the implied (and falsified) predictions like “EVALI will continue until legal vaping products are fully banned”? Or would you have fallen for a good Narrative?

Excerpts

Below are some key excerpts, with weasel words or rhetoric highlighted in bold:

Scientists are just beginning to look at the unknown health impacts of new, tobacco-free nicotine products, even as research is expanding into the harmful effects of vaping and its flavor ingredients.

…Scientists are just beginning to study the unknown health effects of synthetic nicotine, even as research is expanding into the harm caused by vaping and flavor ingredients alongside continuing cases of devastating vaping-related lung injury. To many public health advocates, new trends in the vaping industry are thwarting the FDA’s efforts to protect a new generation from nicotine addiction.

…FDA enforcement actions have had little effect on Lizzie Burgess’s ability to get vapes over the last 4 years. “I think the FDA should take it all off the market now”, she said.

…Vaping is still popular among teenagers. Rani Dhiman, 16, said it is highly visible in the bathrooms and stairwells of her high school in the Detroit suburbs.

…She said the stress and loneliness of the pandemic might have been a trigger for some teenagers to start. It’s also portrayed glamorously, she pointed out, in “Euphoria”, a popular HBO series about a teenager kicking drug addiction.

…The FDA’s efforts to limit teenagers’ access to flavored vapes had little effect on Lizzie Burgess’s ability to get them over the last 4 years in the Indianapolis suburbs. Within weeks of starting to vape at 16, she said, she was addicted. There was always a gas station, older friend or website selling e-cigarettes in flavors like banana ice cream or sour apple, she said.

…At 19, she said, she was vaping THC and using a device—now advertising tobacco-free nicotine—that has as much nicotine as two packs of cigarettes, every 2–3 days. She said she fell ill with what started like a cold, which progressed to rapid breathing, almost-gray lips and feeling depleted. By the time she went to the emergency room, her oxygen saturation was 67, far below the normal range of 95 or higher. Burgess said she was soon in the ICU with vaping-related lung injury.

[photo of young woman in ICU with face covered by a medical ventilation mask]

[Burgess in the ICU last year. When she arrived at the hospital, her oxygen saturation was 67, far below the normal range of 95 or higher. Credit: Lizzie Burgess]

[X-ray scan of two pairs of lungs. Top: “Liz’s Lungs”, off-color and shrunken. Bottom: “Healthy Lungs”, white and large.]

…She’s struggled to end her nicotine addiction and is down to two cigarettes a day.

…“I think the FDA should take it all off the market now”, Burgess said of the flavored vapes. “I think it will be very very hard for them to reel it all in. It’s so big and there are so many companies now.”

…[Sales data] released by the CDC Foundation shows that since the FDA stepped up e-cigarette enforcement in February 2020, sales of disposable fruit-flavored and candy-flavored devices have grown by 290%, to 6.46 million devices a month by November 2021. Sales of the FDA-targeted flavored pod and cartridge devices have nearly vanished.

…The unregulated vaping market at this point is a problem of the FDA’s making, said Gregory Conley, president of the American Vaping Association, an industry trade group. He said the agency fueled the problem by over-regulating a product used by millions of adults who find vaping a safer alternative to smoking.

…“This country should learn some lessons from past prohibitions that failed miserably”, Conley said. “If you don’t fairly regulate a market where there is a great deal of demand from legal adults, you will fuel gray and black markets where the operators are not concerned with checking IDs before selling.”

…Recent research has focused in on the chemicals used to simulate butter, which is linked to lung damage, and vanilla, which is associated with birth defects in zebrafish.

External Links

Discussion: HN

Appendix

The NYT Article

“The Loophole That’s Fueling a Return to Teenage Vaping: Sales are rising of flavored e-cigarettes using synthetic nicotine that evades regulatory oversight, a gap that lawmakers are now trying to close”:

By Christina Jewett

March 8, 2022

[image of assorted vaping products on a white table]

Scientists are just beginning to look at the unknown health impacts of new, tobacco-free nicotine products, even as research is expanding into the harmful effects of vaping and its flavor ingredients.

The Food and Drug Administration’s crackdown on flavored e-cigarettes in 2020 was meant to be a comprehensive, aggressive strategy to curtail the epidemic of teenage vaping.

But two years later, sales of disposable, flavored e-cigarettes have soared. Some companies have moved just beyond the reach of the FDA by swapping out one key ingredient. They have circumvented federal oversight of tobacco plant-derived nicotine by using an unregulated synthetic version.

The agency had nearly wiped out the use of flavors in devices like Juul, once the teenage favorite, that could be refilled with pods in flavors like creme brûlée and mango. Jumping into the breach, though, companies like the teen favorite Puff Bar are selling disposable devices filled with candy flavors and tobacco-free or synthetic nicotine.

Scientists are just beginning to study the unknown health effects of synthetic nicotine, even as research is expanding into the harm caused by vaping and flavor ingredients alongside continuing cases of devastating vaping-related lung injury. To many public health advocates, new trends in the vaping industry are thwarting the FDA’s efforts to protect a new generation from nicotine addiction.

“These companies like Puff Bar and others are deliberately driving their trucks of poison through this huge loophole”, said Meredith Berkman, a founder of Parents Against Vaping E-Cigs. She recently hosted a webinar about synthetic nicotine attended by 700 people. “We think we need to regulate these products.”

Lawmakers on Tuesday proposed language that they want inserted in the Congressional omnibus budget bill that would give the FDA authority to regulate synthetic nicotine, although it is unclear if the issue will be included in the final bill.

Representative Frank Pallone Jr. Democrat of New Jersey and chairman of the House Energy and Commerce Committee, said the provision would be a public health victory over “bad actors” who circumvented the FDA’s authority.

“That ends with passage of this bill, which will close this loophole and clarify FDA’s authority to regulate all tobacco products, including those containing synthetic nicotine”, Pallone said in a statement on Tuesday.

Sales of synthetic or tobacco-free nicotine went from virtually nonexistent in 2020 to taking up shelf space in 2⁄3^rds of US vape shops in 2021, according to market research. Those stores said such products accounted for nearly 20% of sales, according to ECigIntelligence, which surveys hundreds of the shops each year. The company projected that the US vape market, web sales included, would be nearly $6 billion this year.

FDA enforcement actions have had little effect on Lizzie Burgess’s ability to get vapes over the last 4 years. “I think the FDA should take it all off the market now”, she said.

[Photo of young white woman in a bomber jacket and jeans, looking sad.]

[Credit: Lee Klafczynski for The New York Times]

Federal officials have been in a cat-and-mouse game with some e-cigarette makers. Spurred by a court order, the FDA forced thousands of e-cigarette companies, including Juul, to apply in 2020 for authorization to remain on the market. With the agency focused on the most popular devices, like Juul’s, that used insertable cartridges, makers of disposable vape pens in flavors like gummy bear and candy cane flooded the market. The agency then responded with a stern warning and even product seizures aimed at some of those companies, including Puff Bar.

By late last year, more than a million tobacco-sales applications had been denied. Applications to remain on the market by Juul and myriad other companies are pending.

By early 2021, Puff Bar returned to the market with “tobacco-free” or synthetic nicotine that didn’t fall under FDA oversight, loaded with the fruity flavors prohibited in vapes with tobacco-based nicotine. Other companies imported similar devices containing synthetic or tobacco-free nicotine from factories in Shenzhen, China, according to industry experts.

Patrick Beltran, who has identified himself in news reports as one of two executives of Puff Bar, did not respond to requests for comment.

Sales data released by the CDC Foundation shows that since the FDA stepped up e-cigarette enforcement in February 2020, sales of disposable fruit & candy-flavored devices have grown by 290%, to 6.46 million devices a month by November 2021. Sales of the FDA-targeted flavored pod and cartridge devices have nearly vanished.

Since early 2020, overall e-cigarette sales are up nearly 50% to about 22 million units per month, according to Information Resources, a data tracking consultant. The National Youth Tobacco Survey conducted in early 2021, when many students were learning via Zoom, reported that, overall, about 11% of high school students used e-cigarettes.

New e-cigarette suppliers can go into business easily: They contract with a manufacturer in China, set up a website and get space in a warehouse to store and ship devices, said Samantha Shusterman, a senior counsel supervising e-cigarette enforcement for the Massachusetts attorney general’s office. They use shell companies and can quickly withdraw the profits if they face scrutiny.

“It’s a whack-a-mole situation”, said Shusterman, whose state banned all flavored e-cigarettes, except in licensed smoking bars. “They’re not following any of the laws.”

Mitch Zeller, director of the FDA’s Center for Tobacco Products, said the agency recognized the problem.

“Disposable e-cigarettes made only with synthetic nicotine pose a particular challenge for the FDA when it comes to our tobacco authorities”, Zeller said in an email. “The FDA is actively investigating this issue and considering how to best address such products.”

[photo of young woman in ICU with face covered by a medical ventilation mask]

[Burgess in the ICU last year. When she arrived at the hospital, her oxygen saturation was 67, far below the normal range of 95 or higher. Credit: Lizzie Burgess]

[X-ray scan of two pairs of lungs. Top: “Liz’s Lungs”, off-color and shrunken. Bottom: “Healthy Lungs”, white and large.]

[A scan of Burgess’s lungs, top, compared with healthy lungs. Credit: Lizzie Burgess]

Vaping is still popular among teenagers. Rani Dhiman, 16, said it is highly visible in the bathrooms and stairwells of her high school in the Detroit suburbs.

She said the stress and loneliness of the pandemic might have been a trigger for some teenagers to start. It’s also portrayed glamorously, she pointed out, in Euphoria, a popular HBO series about a teenager kicking drug addiction.

“Sometimes so many people are vaping in the bathrooms, it’s hard to do anything about it”, Dhiman said, adding that she doesn’t vape.

The FDA’s efforts to limit teenagers’ access to flavored vapes had little effect on Lizzie Burgess’s ability to get them over the last 4 years in the Indianapolis suburbs. Within weeks of starting to vape at 16, she said, she was addicted. There was always a gas station, older friend or website selling e-cigarettes in flavors like banana ice cream or sour apple, she said.

At 19, she said, she was vaping THC and using a device—now advertising tobacco-free nicotine—that has as much nicotine as two packs of cigarettes, every two → 3 days. She said she fell ill with what started like a cold, which progressed to rapid breathing, almost-gray lips and feeling depleted. By the time she went to the emergency room, her oxygen saturation was 67, far below the normal range of 95 or higher. Burgess said she was soon in the ICU with vaping-related lung injury.

She’s struggled to end her nicotine addiction and is down to two cigarettes a day.

“I think the FDA should take it all off the market now”, Burgess said of the flavored vapes. “I think it will be very very hard for them to reel it all in. It’s so big and there are so many companies now.”

Synthetic nicotine remains far more expensive than the tobacco-derived product, leading some industry experts to question whether a device label of “synthetic” is accurate.

The unregulated vaping market at this point is a problem of the FDA’s making, said Gregory Conley, president of the American Vaping Association, an industry trade group. He said the agency fueled the problem by over-regulating a product used by millions of adults who find vaping a safer alternative to smoking.

“This country should learn some lessons from past prohibitions that failed miserably”, Conley said. “If you don’t fairly regulate a market where there is a great deal of demand from legal adults, you will fuel gray and black markets where the operators are not concerned with checking IDs before selling.”

[Photo of professorial old white man sitting on desk]

[Dr. Robert Jackler of Stanford University created a “synthetic teenager” named Joe, who used gift cards to buy flavored synthetic nicotine products online and have them shipped. Credit: Ian C. Bates for The New York Times]

Dr. Robert Jackler, who studies tobacco company advertising at Stanford University, has also noted major tobacco retailers entering the synthetic nicotine market with flavored gums called “pouches.” He said his tobacco research group could pose as a teenager and use gift cards to easily buy the flavored synthetic nicotine gums from major retailers and have them shipped to a home in California.

“When we buy them, there’s no age gating”, Dr. Jackler said.

The loopholes are many with synthetic nicotine, he said, allowing the products to avoid hefty tobacco taxes and remain affordable and to evade the algorithms that online retailers use to weed out underage sales of tobacco products. The ease of purchasing was also concerning, Dr. Jackler said, given how little is known about the health effects of flavored, synthetic nicotine.

Recent research has focused in on the chemicals used to simulate butter, which is linked to lung damage, and vanilla, which is associated with birth defects in zebrafish.

Dr. Sven-Eric Jordt, an associate professor at Duke University who has studied synthetic nicotine, said it posed many unknowns.

About 99% of tobacco-derived nicotine is a psychoactive molecule called S-nicotine, he said. But a mirror-image molecule, known as R-nicotine, makes up 50% of most types of synthetic nicotine. He said the R-nicotine molecule appears to be less addictive, but very little research has been done on it in animals or humans.

“It could alter nerve transmission in the brain in different ways from classic nicotine”, Dr. Jordt said, “but we don’t understand that at this time.”

Comments

NYT reader comments, mirrored to show how the article’s framing was received.

Off-brand vapes with real nicotine are trivial to find and buy. All the FDA’s ban did was drive users to less safe products, which is exactly what anyone paying attention predicted at the time.

Vaping hasn’t been shown to be unsafe scientifically. I don’t do it; I don’t like it. But this ban did exactly what every ban in history has done: No one vapes less, but now there are fewer quality (and health) controls.

It would be great if the New York Times could get perspectives from informed harm reduction advocates, who understand that vaping nicotine is not dangerous.

Charles A Gardner would be a good voice on these issues.

Shame on the legislators who wrote the bill and didn’t close this loophole. They were either ignorant or complicit.

Hmmm chemicals that make meth fentanyl and puff vapes all get their chemicals from China and the bought off politicians who represent us are paid off, sounds like the Chinese are returning the opium wars of the 19^th century on us.

I don’t drink, smoke cigarettes or pot, use drugs, gamble for money, cheat on my wife or my taxes. ride motorcycles, put on tattoos, ski down mountainsides, go on hikes alone in the forest, believe in bitcoins or eat at roadside restaurants with signs that say “Good Eats.” And I do ever not count on the government or my next door neighbors to shovel the snow off of my sidewalk for me, Who am I? I am a believer in G—d’s great hidden 11^th Commandment: “First Above All Else, Take Good Care Of Yourself.” Am I the last normal, decent, careful, self-sufficient American still alive?

Synthetic nicotine needs to be put under the regulatory authority of FDA. The fact that these companies can sell synthetic nicotine e-cigarettes without scientific data on their purity and biological effects is highly concerning.

However, in the end this step will help Big Tobacco the most. Synthetic nicotine threatens Big Tobacco’s business model. Only Big Tobacco has the money to pay for the complex toxicological and behavioral studies needed to get marketing approval for e-cigarettes by FDA. At this time, only 1 e-cigarette product, manufactured by RJ Reynolds, has received market authorization by FDA, while millions of applications were denied. The products with synthetic nicotine will likely suffer the same fate, since manufacturers don’t have the funds for the FDA applications.

Thus, the revised legislation will, in fact, be a boon for Big Tobacco. It is likely that it will be supported by legislators on both sides, the legislators in the pocket of Big Tobacco, and legislators concerned about public health.

None of the rhetoric from politicians about synthetic nicotine, or vaping in general, is about preventing youth access or preventing disease. It’s about money. MSA payments from the cigarette companies to the States from [??] totaled ~$178.1 billion—but these same States have spent only ~$0.72 billion on Tobacco Prevention. If cigarette consumers switch to vaping, the States lose ever increasing amounts of their general funds.

@RuthieB—we keep telling them but it goes in one ear and out the other. Which is exactly what the states, the politicians and the tobacco companies want. It’s where the money lies.

This was so predictable—in fact, many did predict it, including laypersons like myself. These companies don’t care about health, particularly children’s health, if they see a market for their product. One company, Vuse, is now even marketing itself as “environmentally progressive” because they have removed the plastic wrappers from their products, thus eliminating tons and tons of plastic from the planet. Yet they don’t talk about the vapors that addict and kill people—including children—and also pollute the air. These companies are reprehensible and have absolutely no regard for human life.

@Maani Rantel—We’ll, big tobacco and big Pharma don’t care about anything but profits. And they don’t have to worry about ‘carding’ people. There is where your problem lies! If there were only small business vapor shops there wouldn’t be a problem. THEY card. They care about their business. And they care about the product and it’s refill ingredients. But when you only target the general product then you get what you got. All the products in the article picture are from those big companies. Everyone loses then. Lies spun around a great innovation that drops lethal hazards to a person by 95–98% are more believable than the truth. People want to believe those negative stories. It’s easier than actually doing their own reading on all the research done by responsible doctors/researchers. Just why didn’t they try to destroy the tobacco companies instead? With nothing good coming out of a cigarette why are they still on the market? Plenty of research on them. Wait…you have to read.

@Maani Rantel One thing this article completely misses is the fact that no nicotine-based e-cigarette (tobacco-derived or synthetic) is known to have caused a single death. Not one, ever. Compare that to 1,300 deaths DAILY from combustible cigarettes. The illness described in the article was clearly caused by using an adulterated, illegal, THC-containing vaping product, not the nicotine-based e-cigarettes being criticized here. That should have been made clearer. Nicotine does NOT cause the diseases caused by inhaling smoke, or nicotine medications would be deadly—but the FDA approves them (correctly) as both effective and safe. The illnesses and deaths result from 70 known carcinogens and other toxins in SMOKE, produced when the contents are burned. People need to understand these differences.

How pathetic is our country, the land of the free, when young adults can serve life sentences but cannot drink a beer or vape? If kids are mature enough to be charged as adults than they should be able to decide what goes in their bodies.

“Federal officials have been in a cat-and-mouse game with some [drug] makers.” this is why trying to ban cannabis (and other drugs like cocaine) has failed, and in some cases violently so, for various parties involved. moreover, prison sentences offer their own costs when the mice are caught. fines or community service could be a substitute, and in some cases they are. as for nicotine, no article is complete without a comparison with combustible and other forms of tobacco, both in terms of consumption patterns (for minor users) and in terms of laws and their applications. Various surveys show that traditional tobacco consumption is at historic lows, especially for minors.

I’m confused as to how these companies can “circumvent federal oversight” by using synthetic instead of plant-based nicotine. I don’t think you can “circumvent” the federal oversight of mescaline, by making it in a lab and possessing it, instead of possessing peyote (plant-based source). Can anyone shine a light on the discrepancy?

@Med Chem Guy I actually work at a vape shop in Pennsylvania. We scan every ID to make sure no kids are getting anything. So, the legislation that (as of writing) currently is in place bans any flavored TOBACCO products. Because the nicotine is not sourced from tobacco it was technically allowed.

The solution is obvious: states and municipalities should impose exorbitant “sin taxes” on these products as to make their purchase out of reach for teenagers, most of whom are of limited means.

While legalized prohibition has been a disaster and a prime example of the “cure” being far worse than the disease, making these products prohibitively expensive by means of aggressive taxation, policies which could put a deep dent in the sales of vaping devices.

The revenue generated could then be used to fund smoking cessation and substance abuse programs along with public service advertising, all of which could be of help in reducing the damage to health which is becoming associated with the use of synthetic nicotine.

@mosenblum this is absurd. People have a right to engage in activities of their choosing without overreach from the federal and or state government. Why should the same thinking not apply to any other so-called vice? Should junk foods be exorbitantly taxed? How about sex toys? Leave and let be.

@mosenblum—first, parents are buying these ‘devices’ for their teens. And second, teens have their own credit cards, their ‘means’ are more than you realize. And third, where’s the sin part in an electronic cigarette used for tobacco harm reduction? The thousands of dangerous and dirty chemicals are missing. There’s no tar. It doesn’t cause disease it prevents it…so where’s the sin to tax? See, here’s the example of people only listening to social media and false information instead of researching for themselves.

I had recently turned 21 when we were told that second-hand smoke had been proven so definitively to be harmful that it was banned in bars and workplaces. My state banned vaping in bars and workplaces before a single study had shown any harm was caused by the mist created by such a device. At some point we should acknowledge that in addition to well meaning and science-backed regulation, we have allowed prohibitionists to lead the discussion and paint everything they don’t like as something that needs to be forbidden to all.

@Brian M The studies that found the danger in second hand smoke were epidemiological studies that found higher rates of cancers (among other ailments) in people with high exposure to second hand smoke. How long and how many dead should there be to test out the “mist” of a vape, sir?

It is NOT just a “mist” that vapers exhale. There are many chemicals and heavy metals in the liquid that is burned. Young people especially become easily addicted to the nicotine because it is so EASY to learn how to vape because the vapor is cool. Some kids vape 2 or more pods a day—equal to 2 packs of cigarettes a day. The damage to their lungs resembles the worst pneumonia you can get and still be alive. Adults who think vaping might aid them quitting smoking regular cigarettes more often just become double users and are just as addicted.

You make a valid point. Perhaps my choice of “mist” was loaded. I should have said “aerosol byproduct” or any number of things that do not sound as innocent as mist.

Let them vape. Let them smoke. Let them take drugs. Let them drink. Let them eat cake. Where there’s a will, there’s a way. People, whether 14 or 44, are going to do what they want to do. The government and industry can not stop it. And actions have consequences. Perhaps many will learn their lesson before it’s too late. And if not, so be it. Like with Covid, too much time is spent on bemoaning those who do the wrong thing. Society will benefit when those who care more about getting high, no matter how it impacts themselves or others, learn that they’ve made mistakes. I suspect ending up in an ER will be a valuable teaching tool.

These companies are intentionally targeting and addicting tweens and teens to a highly addictive product that over time will prove to be disastrous for their respiratory systems. Instead of weak kneed regulation of the industry, the FDA might want to get a backbone and outlaw sales as a health measure that will save countless young people misery in adult life.

The War on Vaping will, I’m sure, turn out to be worth it years from now. Remember how we got rid of drug use?

@Seymour Butz—People should watch “https://m.youtube.com/watch?v=9vh_YzyzUys It’s called The Fix on Roku TV. I found it on YouTube too. It’s basically about drugs. However, it’s very eye-opening. Tells you how we all have been lied to. Just like this topic. You all are being lied to on such a high level it boggles the mind. Why are they not targeting cigarettes‽? Still on the market. Research by the droves proving the dangers. Yet they skip that step and target the harm reduction innovation that left out thousands of chemicals, carcinogens and tar.

The purveyors of these drug delivery systems are killing our children with intent. They should all be thrown in jail, and the import of these products should be banned. This is vile.

Predatory business practices. Perhaps the area of business that the consumer protection agency is responsible for should be expanded.

Ah the cigarette company executives are at it again. After spending decades during the 20^th century and tens of millions of dollars in legal fees blocking the medical facts from the public that smoking causes lung cancer and emphysema, here they are exploiting a legal loophole to addict millions more young adults to their lethal products. And I bet they’ve got dozens of lawyer/lobbyists on Capitol Hill trying to defend this loophole. What a surprise! Like the old saying goes—history repeats itself.

Tempting I’m sure to suggest legalization and taxation, but the issue isn’t as clear cut here. The issue is that kids are using these like candy, because they taste like candy and are being marketed like fun candy times. It was one thing, “back in the day” for most parents (myself as a teenager in the 90s included), where it was tough to hide smoking, because smoking stinks. The smell sticks to you and follows you around. Now we have these USB devices, with a smell that can be easily overlooked, assuming one even notices. Your sons and daughters can use this despite all of your best efforts. And no, “education starts at home” is not a public health policy we can all rely on. The simple reality is that these need to be flat-out banned. We don’t need every detail right now to be millimeter precise about it—just pass a blanket ban and plug the holes as needed.

Smoking causes 480,000 deaths (COPD, strokes, cancer) per year in the US. And you want to have the most effective quitting option banned? Because the teen experimentation accelerated the decline in youth smoking rates? Unlike what the framing campaigns suggest, e-cigarettes weren’t invented by Big Tobacco, nor are they anywhere near as harmful or addictive. (Tobacco isn’t just nicotine. They sure made people believe it though.) You know, before going for another super successful prohibition attempt, might be worth checking out marketing regulations, or better sales enforcement. With the caveat that absolute prevention will force teenagers to relapse to smoking. (And that’s probably what these AstroTurf articles are really about. Adult relapse or handing the vaping market over to Big Tobacco is just a nice side effect.)

Just legalize it. People are never going to not want nicotine. Tax it heavy and use the money to help people.

These products are legal, for adults. The whole point being at that age you are informed enough to make a decision about your health and the possible risks. I’m not naive, I snuck cigarettes when I was a teenager, but allowing kids wholesale access to these products (which deliver far more nicotine than traditional cigarettes) doesn’t seem like the answer.

You don’t put out a wildfire by pouring gasoline on it.

Error: JavaScript disabled.

Backlinks, similar links, and the bibliography require JS enabled to load.

Top-k Reading: Against Polishing the Median Essay

Gwern Branwen — Mon, 11 May 2026 00:00:00 GMT

How should a writer trade off new writing (exploration) against polishing old writing (exploitation)?

I suggest a simple order statistics toy model of readers with a finite ‘window’ of reading time for an author’s best writing, where each new writing has a chance of being good enough vs polishing an old favorite. A new writing only matters if it enters the window; an edit only matters if it improves something in the window.

The implication is simple. Polish when a marginal edit improves work inside many readers’ windows: consensus hits, durable pieces, introductory essays, or high-stakes publications. Write more when readers have large windows, heterogeneous tastes, or when a new topic can create a different local hit for a different audience.

For eclectic generalists with diverse readerships like me, the strategy is not to perfect the median piece. Instead: polish the winners, ignore mid-tier work, and keep trying to create new local hits.

Years ago, I discussed the apparent “perfection premium” in polishing writing, and how a writer should quickly hook readers upfront in a new writing. But how should we think in the first place about polish in writing vs new writing?

The Trade-Off

Most writers online, I think, give up relatively soon. This is not because we ran out of things to do—there’s always another typo we could fix… But when we choose to spend our limited time and energy hunting for typos or fixing formatting, there’s a definite sense in which we decide it’s no longer ‘worthwhile’ trying to improve old writing after some point, and we’re better off doing new writing.

But this is a little odd: if we’re not ‘done’ with old writing, why should we start something new? And if we have a large backcatalogue, we can hardly plead poverty of material; how can I argue with a straight face that my readers lack for things to read and so it is imperative I go write something new rather than polish an old popular essay?

Marginal returns. The economics or optimal foraging answer would be the heuristic ‘you should switch between whichever has the highest marginal return at any given moment’—but marginal return of what? Even assuming we have some ‘utility’ definition we’re satisfied with, how, exactly, does writing turn into that? If I write an essay or I polish an old one, what does that mean for a reader?

A toy model that seems plausible to me is that what is going on is that each reader has a certain finite size or appetite or window of time, which a writer tries to fill up as best he can. (I’ll use time as my unit here instead of number of words or essays, because I think that increasingly, it is time and attention which is the bottleneck.) One reader has a window of 5 minutes of ‘Gwern reading time’ a year, while another has 50 minutes, and a big fan has 500… The absolute size of the backcatalogue doesn’t matter for each reader—only the best k minutes of your writings.

So, when you write, if a new piece doesn’t make it into the top-k and is only the k+1^th best reading-minute, then a reader doesn’t care. They’re never going to see it and it doesn’t exist for them.

This helps account for why writing is such a “hit-driven business”: after a while, no matter how prolific you are, it makes zero difference to the reader, because you filled up the top-k in their window and nothing budges after that.

Self-Cannibalization

To move the needle, you need to beat your best and push something out of their window. And frustratingly, once you do that, the reader is only slightly happier with you!

Net, not total. This is because you are cannibalizing yourself. If you wrote something which was a +10 in some Quality Unit, and then you write something which was +11, you feel proud of yourself for adding a +11 and thus writing a total +21 of text—that was hard work—but as far as the reader is concerned, it’s just a net +1 because your +11 pushed out the +10.

Perversely, the more you write, the harder it gets to improve your window. If a reader has a window of 10 essays and you’ve written 100 essays to date, then your next essay has to beat >90 of your prior essays to make it into the window at all!

Simply put, I think you should polish in inverse proportion to how much of your writing a reader will see; the more diverse your writing, the better off you are writing more rather than better.

Order Statistics

Rank entry. We can treat this statistically using order statistics; for example, if we imagine some normally-distributed quality statistic, our expected gain is only:

R simulation of the marginal gain from adding 1 normally-distributed piece to a 100-piece back catalog with a 10-piece reader window.

set.seed(2026-05-11)

windowGain <- function(backlog_n = 100, window_k = 10, simulations = 1e7) {
    mean(replicate(simulations, {
        old_quality <- rnorm(backlog_n)
        new_quality <- rnorm(1)
        cutoff <- sort(old_quality, decreasing = TRUE)[window_k]

        max(0, new_quality - cutoff)
    }))
}

windowGain()
# [1] 0.0474129394

~0.05σ better—which is almost invisible percentile-wise.

Equal odds. The simplification of treating pieces as independent samples is crude, but it resembles the equal-odds model summarized by Jung et al 2015: hit-rate is approximately stable, so quantity matters because it buys more rolls of the dice. For writing, this assumption is partly defended by offsetting forces: positive factors like experience are offset by negative ones like using up ideas.

Lumpy returns. More realistic distributions do not change the basic rank fact. With n old pieces and a k-piece window, a new independent piece enters the window with probability k⁄(n+1), distribution-free. A power law or other heavy-tailed quality distribution changes the payoff conditional on entry, not the entry probability: the process becomes more hit-driven, with long stretches of zero marginal value punctuated by rare large replacements.

Polish the Window

Guaranteed gain. This also adds a little insight to the value of polish: while it’s true fixing typos in your best writings doesn’t make them much better, it does make them a little better… And importantly, it’s making the writings in the window better. When you write a new one, you usually fail to replace something in the window, rendering it moot, and if you do, it’s probably a modest improvement; but when you edit the writings in the window, you are getting a small but guaranteed improvement.

Tiny windows. This sheds some light on why you might escalate your quality standards going from a blog post to, say, a New York Times article. (Jasmine Sun mentioned in a recent Q&A at Inkhaven 2 that her NYT piece on peptides might have 10 million readers total, vastly exceeding her lifetime total of Substack readers—so of course she spent months sweating every detail!)

Decay. Meanwhile, a breaking-events periodical newsletter like Zvi Mowshowitz’s will often not bother to fix typos or broken URLs, because the temporal decay guarantees even a good issue will soon drop out of the window, and it needs to rush to write the next one.

For the former, you are talking to a small steady audience with a large window; there’s little point in polishing it. But for the latter, you may get only one, and so the window is small—you’d better make it as good as you can!

Heterogeneity

So, to the extent that your readers are homogenous and have a small window and a universally shared ranking, the better off you are, after a while, trying to polish your writing winners, because you aren’t going to easily beat them but you can still make them a bit better.

But to the extent that they have large windows or heterogeneous different rankings (eg. readers prefer completely different articles), you’re better off just writing more in the hopes of getting a new better one into their windows. The marginal return on every new essay may be quite low (because its topic will appeal to only a small fraction of readers) but it is also true that the return is even lower on polish (because those too are niche but the effort is constant). In the extreme case, every reader has a window size of 1 and prefers a different essay… So you are best off spending 100% of your time writing on a new topic every time, because each one will find a different audience.

In full generality, we could advise a writer to polish in proportion to:

(1⧸Window) × Homogeneity × Shelf-life × Stranger-fraction

And to write more in inverse proportion to all 4.

Eclectic Generalists

My case. For my writing, I think it falls into the latter group: I do not write for prestige or popular periodicals, but on many topics for different readers (eg. darknets vs poetry vs AI vs genetics…). This also describes writers I am sometimes grouped with, like Scott Alexander or Tyler Cowen’s Marginal Revolution. We all share, if nothing else, a generalist eclectic approach. Under this model, Scott Alexander, who has a recognizable ‘beat’, should probably invest more in polish, while I should emphasize more diverse new writing rather than over-polishing, and Tyler Cowen is probably fine in his omnivorous niche of writing about anything with no polish.

Self-indulgence. So I should be writing a lot more on more topics, instead of falling into the artisanal/hobbyist/indie-creator trap of spending as much time as I do on polish and infrastructure. What can I say? I don’t write to be popular, and the polish is for me a personal esthetic and an ethos, not a calculated strategy. (I try not to pretend otherwise, and I tell any aspiring writer who asks that they definitely should not try to imitate Gwern.net but focus on writing. They have my permission to fiddle around with typography after they have, let’s say, a million words—at which point they may have some writing worth polishing.)

But other writers might find this a helpful frame: do your readers have a lot of appetite each, or a little? And are they homogenous or heterogeneous? This can help guide you in deciding how much to invest in copyediting, illustrations, marketing, etc.

Error: JavaScript disabled.

Backlinks, similar links, and the bibliography require JS enabled to load.

Bibliography

[Bibliography of links/references used in page]

‘Try, Score, Change’: Reinforcement Learning for Children

Gwern Branwen — Sat, 09 May 2026 00:00:00 GMT

This is an explainer of deep reinforcement learning, written for children, in the controlled-English dialect Grow-Speech, by LLMs, as an experiment in creative nonfiction writing.

Grow-Speech requires all multi-syllabic words to be defined before use, and my hope is that this trick can help demystify the field of reinforcement learning, which, despite intimidating mathematical apparatus and unfamiliar jargon, often comes down to a surprisingly simple trick or approximation—just applied at scale.

Read This First

This is a text on how a brain can learn to walk a maze, win a game, or chat with you. It learns not just from rules told to it, but from a loop: try, score, change.

I will not start with a long list of new words. A long word will come up when I need it. The first time I do, I will mark it in bold and tell you what I mean. Then that word is mine to use as I please.

Read this with a school room in mind. A black board is up front. A piece of chalk is on the rail. A row of jars, a heap of stones, a short leash, a sketch pad, a chess board, and 8 cakes sit near by. You could build most of this on the floor.

How the Loop Works

A Brain Made of Small Parts

By wire I mean a link in a brain that lets one part send a shock to the next. We run a brain on a chip; and by chip I mean a small flat thing made of wires that does fast math. A brain is made of neurons, and by neuron I mean a small part of a brain that takes in shocks from wires and sends out shocks too.

Each neuron gets shocks from the rest through wires. If those shocks add up past a high mark, the neuron fires and sends out a shock too.

We change how a brain thinks by changing how strong each wire is. We can change the high mark too. Then one neuron may fire more, and one may fire less. That is what folk mean when they say, “the brain learns”.

Here is the prop for wires. Think of each wire as a small jar full of stones. The more stones, the stronger the wire. To make the wire strong, drop a stone in. To make it weak, take a stone out.

When the brain does well, we may add stones to the wires that helped. When it does ill, we may take stones out. Once you can flip wires from strong to weak and back, you can make a brain learn.

Try, Score, Change

A brain learns to do well at a task by try and miss. At each step, the brain looks at where it stands, picks a move, and the world hands back a score. By score I mean a count of points the world hands back: high means good, low means bad. High score for a good move. Low score, or no score, for a bad one. The brain wants the best score it can get, on the whole, in the long run.

Think of a dog and a treat. You do not tell the dog all the rules. You just give it a treat when it sits. Soon, the dog sits to get the treat. A bot is the same: hand it score, and it learns to do more of what got score.

Or think of a small bot in a maze. It steps left and hits a wall. Bad score. It steps right and finds cheese. Good score. At first, the bot knows no path. It has to try, get score, and change.

By reinforcement learning I mean a way for a brain to learn from score.

Reinforcement learning is not a spell. It is not joy or pain in the bot. The score is just a count that tells us how to change the brain.

Thanks and Blame

The hard part is thanks and blame. The score for a move can show up long past the move that earned it. The bot might step left, then up, then up, then right, and then find cheese. Which step earned the cheese? The last step? A step 10 steps back? Each step in the chain wants its share. But the world hands back just one score at the end. So the brain has to spread that score back through the chain.

This is the core hard task: hand thanks and blame to the right past moves. Each way to learn that we will see is a way to crack this. None of them are quite right. On the whole, they work. On the whole.

Try New Things or Use Old Ones

At each step, the bot feels two pushes.

The first push says: do what worked best so far. You know that move. It gave you score. It is safe.

The next push says: try a new thing. A new move might not be like you thought. It might be much, much better than the old one. But it might be a waste. Or a trap.

These two pushes do not pull in the same way. You can not do both at once.

These two pushes have one name: the explore-exploit trade-off: Explore means try a move you have not tried much, or one that looks weak now, just in case it is strong; Exploit means pick the move that looks best from what you know now.

You face this too. Think of the town book room. You have a card that lets you take home one book each week. You know the first shelf well. You have read 3 books from it and loved each one. Right next to that shelf are 50 more shelves you have not yet looked at. One of them might hold a book you would love more than the 3 you know.

Each week, what do you do? Walk to the shelf you know and take out a sure good book? Or skip that shelf, walk to a strange one, pull a book at chance, and risk that it is bad?

You can not have both. The book you take this week is the one you take. The bot has the same choice, each step.

Most ways to learn fudge this with chance. Most of the time, exploit and pick the best known move. Now and then, explore and pick a move at whim. As the brain gets sharp, drop the chance of wild tries. The blunt knife works.

But in hard worlds—where one rare, strange move will lead to the huge score—you need a smarter blend. That is why we still look for the best way to explore.

For now, just learn that there are two pushes. The explore-exploit trade-off is in all games. A good bot feels both and chooses well.

State, Move, Score, Plan

We need some more words:

A state is how we sum up where things stand now, like what the brain sees right now: the spot in the maze, the board in a game, the words on a chat screen.
A move is what the brain does next: step left, push a pawn, write a word…
A score is the count the world hands back.
A plan is what the brain does in each kind of state.

By policy I mean a plan for what move to make in each kind of case.

Think of a policy as a rule book. One page per kind of state. Each page says, “if you see this, do that”. Some pages are firm: “do this one move”. Some are loose: “most of the time go left, but with some chance go right”.

By value I mean a guess at how much score will come from a state or a move.

Think of a value as a price tag. It may sit on a state: “this place looks good”. It may sit on a move: “this move looks good from here”. At first, the price tags are blank. The bot has no clue what each move is worth. As it plays, the price tags fill in. A high price tag means good. A low price tag means bad.

One small point on price tags. A score now is worth more than a score far down the road. The far road might not come. The bot might fall in a pit. So the price tag for a move is a sum: score now, plus some score from what comes next, plus less score from what comes past that, and so on. The more far off the score, the less it weighs. That is why a value is a guess at score, not just the score seen now.

Tags On A Board

A Grid of Q

Now we can build our first way to learn, with no big brain at all: just a black board and chalk.

By table I mean a grid of rows and cells, like a calendar or Tic-Tac-Toe.

Draw a grid on the board. Down the left side, write each spot in the maze, one per row. On the top, write each move the bot can make: left, right, up, down. In each cell, write a count: the price tag for that move from that spot. At the start, write 0 in each cell.

By Q-learning I mean a way that fills a table with value guesses through play.

Q-learning goes like this. The bot lands on a spot. It looks at the row for that spot. It scans the row, finds the cell with the best count, and walks that way. Most of the time it picks the best cell; now and then it picks at chance, just to try. It does the move, gets score, and lands on a new spot.

Then it fixes the cell it just used. Look at the new spot’s row. What is the best count in that row? Add the score to that. Now blend the cell’s old count with this new one: rub out a bit of the old, write a bit of the new in its place.

Do this for a long stretch of play, and the counts on the board fill in to the right values. Then the bot just looks at its row, picks the best cell, and plays.

By value-based I mean a way that learns values first, then picks moves from them.

Q-learning is a value-based way. It fills in price tags first. Then to act, it just picks the move with the best price tag. The rule book is built on top of the price tags.

By tabular I mean made with a table, not with a brain.

This is tabular Q-learning. There is no brain of neurons here at all. Just a board and chalk. You have built a thing that learns to play a maze with just what is in your school room! Chalk boards were not meant to think, nor win or lose; try not to brag.

When the Board Is Too Big

Tabular Q-learning works well for small worlds. For huge worlds, the board blows up.

Think of the world a chess brain sees. A board has 64 squares. Each square holds one of 13 things: 6 kinds of white piece, 6 of black, or a blank. The count of board states is vast: more than grains of sand on Earth, more than stars in the sky. The black board would have to be wide past your school, your town, and the state you live in. A chat brain has it worse: there is one state per chunk of text it might see, and there is no end to chunks of text.

So we ditch the board. In its place: a brain of neurons. The brain takes in the state, such as the board or the words, and spits out the counts as if it had seen the right row. It is a brain that guesses what the chalk would have said, had we drawn that row.

This is the deep trick: trade the board for a large net of neurons. The rule of Q-learning stays much the same. The brain stands in for the chalk. It can make a fair guess for a state it has not seen, since kin states tend to have kin values. A black board could not do that: chalk in one row does not tell you what to write in the next.

The same swap works for the rule book. A small rule book fits on a board. A chat brain’s rule book has a chance for each next word, and the word set is far too large to draw. So the rule book can be a brain of neurons too. It takes in the state and spits out a chance for each move.

The rest of this text works if you have a board or a brain of neurons. The prop shifts; the loop stays.

Three Splits

Map or No Map

By model I mean a map in the brain of how the world works.

Think of a model like this. The bot has, in its head, a small doll house of the maze. In the doll house lives a small doll bot. The real bot can poke the doll bot through the doll house and see what comes next. “If I send the doll left, then up, where does it land?” The doll house is the model. With it, the bot can plan a string of moves, then move a foot for real.

A bot with no model just plays in the real maze. No doll house. No plan in its head. It steps, gets score, and learns.

By model-free I mean a way that learns with no model. By model-based I mean a way that learns with a model.

Model-based ways can learn from less play, since the brain can plan in its doll house and squeeze more out of each run. But the doll house might be wrong. The doll house could say, “step left and you find cheese”, while the real maze says, “step left and you hit a wall.” Then the brain plans well in the doll house and fails in the real maze.

Model-free is slow but safe: no wrong doll house to fool you.

Tabular Q-learning is model-free. The chalk on the board holds price tags for moves, not a doll house of the maze.

Whose Play Counts?

Now a fine point. The brain is making moves, and it is learning. But is it learning from its own moves right now, or from old game tapes?

By on-policy I mean a way that learns from the policy it has now. By off-policy I mean a way that can learn from old play or a past policy.

If you are on-policy, you learn from fresh games. Once you change your policy, the old games may not fit. They came from the old policy, not the new one. You have to play more.

If you are off-policy, you keep a stack of old game tapes on your shelf. Some are tapes of you last week. Some are tapes of kin bots. You watch old tapes from the stack and learn from them too. This saves fresh play. But off-policy is a fair bit harder to make work right. Old play can point the new policy at the wrong thing.

Tabular Q-learning is off-policy. Why? When it fixes a cell, it blends in the best count from the next row, not the count of the cell the bot would in fact pick next. It learns the value of the best policy, not just the policy it used to get that play. That is what makes it off-policy.

We now have 3 splits to track: (1) price tag or rule book; (2) doll house or no doll house; (3)fresh games or old tapes. Each way to learn can be tagged on all 3.

Shift the Rule Book

Shake and Pick

How do we make a brain, not a board, learn? Here is one way that uses no math.

By evolution I mean change of a kind through births, shakes, wins, and deaths. By strategy I mean a plan for how to win. By evolution strategy I mean a strategy that trains a brain by small shakes and scores.

An evolution strategy goes like this. Take a brain. Make 100 twins. For each twin, give it a small shake: a few wires shift up, a few shift down, by chance. Now race all 100 brains through the maze. Each twin gets a run time or a score. Drop the, say, 90 worst. Then keep the 10 best.

From those 10, make 100 new twins. Shake each one. Race them through the maze. Drop the 90 worst. Keep the 10 best.

Do it once more. And once more…

Soon, the brains run the maze fast!

This is grim if you think too hard. But the brains do not feel a thing. This is in fact how you got here, just on a much longer time scale.

An evolution strategy is model-free: no doll house. The rule book brain is what gets a shake. It is plain on-policy: each score comes from what the brain just tried.

What is the good of an evolution strategy? It is plain. It works on huge brains. You can race all 100 twins at the same time on lots of chips, since each twin runs on its own.

What is bad? It wastes play. A twin has to run a whole maze just to get one score. One bad slip in a long run can make a great brain look bad. Worst, it is dumb to thanks and blame: it pays no heed to which moves in the run helped or hurt. The score is a big lump dropped on the brain as a whole. The next ways are sharper.

One Brain, Lots of Runs

By REINFORCE I mean a rule that makes moves in runs that beat a base more apt, and moves in runs that fall short less apt.

Set a shelf in front of you. On the shelf is a jar for each wire in the brain. The count of stones in a jar tells you how strong that wire is. A jar with lots of stones: a strong wire. A jar near dry: a weak wire.

REINFORCE goes like this. One brain plays a whole run. At each step, it picks a move with some chance. Note each move and which wires helped lead to it. At the end of the run, look at the score. If the score is high, walk down the shelf and drop stones in jars for the wires that helped make the moves. If the score is low, walk down the shelf and pluck stones out of those jars. Then play more runs and do it once more.

This is not fair to the wires in one run. A wire that helped make a smart move in a lost run still loses a stone. A wire that helped make a dumb move in a won run still gains a stone. The jar will not know why. The jar need not know. With lots of runs, the noise tends to wash out. On the whole, wires that help win pile up stones. Wires that help lose run dry. The brain gets good.

By policy-based I mean a way that changes the policy, not just values.

REINFORCE is a policy-based way. It does not fill in price tags first. It just shifts the rule book: make this move more apt, make that move less apt. Policy-based ways tend to work well on huge tasks, such as a chat brain that writes the next word, where there are far more moves than we could rate one by one. Value-based ways tend to work well on small tasks where the brain can rate each move with care.

REINFORCE is on-policy and model-free too. It is sharper than an evolution strategy, since it changes the parts that helped make the moves. But it is still loud. A whole run gives one blunt grade to lots of small moves.

A Judge on the Side

REINFORCE is loud. “High score” is a loud grade for each move. We can get a sharper grade.

By actor I mean the brain that picks moves. By critic I mean a side brain that tries to guess the value.

Set up two brains now. The actor plays the game. It has the rule book. The critic sits on the side and calls the play at the start. At each spot, the critic shouts a guess: “From here, you will score 5 treats.” The critic is graded by how close its calls come to the truth. A wrong call costs it. A right call pays it.

By advantage I mean how much a run beat the critic’s guess.

Now we change REINFORCE. The actor makes a move. The critic called 5 for that spot. The run in fact ends with a score of 8. That beat the call by 3, so the advantage is +3. Drop stones in the jars that helped make that move.

If the run ends with a score of 2, that is short of the call by 3, so the advantage is −3. Pluck stones out of those jars.

Now we are not paying wires for “we won”. We are paying them for “we did better than the critic thought”. That is a sharper grade, and the brain learns faster.

The critic is just a value brain: a brain of neurons that guesses the price tag for a state. So this trick blends policy-based and value-based in one. The actor is the rule book. The critic is the price tags.

Keep the Push Small

Small Steps

REINFORCE and the actor-critic trick have a sore spot.

When you change the brain a lot in one step, you can break it. A brain that was great might, with one big push, lurch off and lose for a long stretch. Worse, it may lose skills it once had, such as how to walk in a straight line.

By PPO I mean a rule that clips the push so a new policy stays near an old one.

Think of PPO as a short leash, but tie the leash to move chance, not to each jar. Keep a note of how apt the old policy was to pick each move it in fact picked. Train the new policy on those same moves. If the new policy tries to make a good move far more apt, PPO clips the push. If it tries to make a bad move far less apt, PPO clips that push too.

The leash is not on each wire. The leash is on move chance.

The old policy picked a move. The new policy may make that move more apt, or less apt. But PPO clips the push if the change gets too large.

So the brain learns by lots of small steps, not by big leaps. Good moves get more chance, but not too much at once. Bad moves get less chance, but not too much at once. This helps keep the brain from a wreck of what it knew.

PPO is policy-based with a critic to cut noise. It is model-free. It is close to on-policy, since it wants fresh runs from the old policy for each round.

The Group Sets the Base

PPO needs the critic brain. That is one more brain to train. It can be hard to make a critic for a chat task. You ask it, “how good will this half done note be once it is done?” The critic shrugs.

By reply I mean text sent back to a prompt. By GRPO I mean a rule that scores a group of replies and uses the group mean as the base.

Think of GRPO as 8 darts at a board. For each task, the brain throws 8 tries: 8 replies, or 8 runs, or 8 ways to solve the same thing. Each one gets a score. Find the mean of the 8 scores. That mean is the base.

Each try that beats the base gets pushed up. Each try that falls short gets pushed down. And you still keep the short leash, the PPO way.

The point: no critic brain. The group is the critic. The mean of the group is the call. Less work, less stuff to train, less to break.

GRPO is a good fit when the score is sharp. For math, did the work come out right: yes or no? For code, did the test pass: yes or no? For chat, a score brain can grade each reply, then GRPO can push up the replies that beat the group.

Slow Think and Games

Lift the Fast Gut

So far, each way to learn has been fast: pick a move and play. But there is a slow way to pick too. You can think hard, then move.

First, use no net. Use the rules of the game. Draw a tree of what-ifs on a sketch pad. At the root is the board you see now. Each branch is a move. At the next row are the boards that could come next. Then the foe moves. Then you move. The tree grows till you stop. At each leaf, write a rough price tag. Then push the best tags back up the tree and pick the branch that looks best. This is slow, but it can be smart.

Now add a fast gut. The fast gut says which moves look worth a slow think. It is the policy. The price-tag head says how good a board looks. It is the value. The slow think uses both: the gut says which branches to search first; the price tag says how good a leaf looks, so the slow think need not play each line to the end.

Here is the loop. The slow think picks a move. Train the fast gut to pick that move with less thought. Then use the new fast gut to guide the next slow think. The slow pick trains the gut. The gut makes the next slow pick better. Round and round.

By expert iteration I mean a loop in which a slow good pick trains a fast gut, and that fast gut helps the next slow pick.

Expert iteration is not a new beast. It is the same old loop in a fine suit: try a strong slow pick, score it through play, change the fast gut to match it.

You can see the old price-tag and rule-book loop in it too. Better price tags make a better rule book. The better rule book makes new play. The new play makes better price tags.

A Game Brain

By self-play I mean play where a brain plays a twin of its own self. By AlphaZero I mean a game brain that lifts its fast gut by self-play and slow think.

Think of a kid in their room with a chess board. The kid plays both sides. White makes a move. Then the kid spins the board, sits in the black seat, and makes a move for black. Spin and switch, spin and switch, all on their own. A few years of this, and the kid is a beast at chess.

That is the feel of AlphaZero. It plays both sides of board games. The raw names of the games were “chess, shogi, and Go”. It got great at all 3 with no help from folk who knew the games. It read no books on chess. It watched no tapes of grand chess play. It just learned from games it played on its own.

The rules of chess are known. If you have a board and a move, the rules tell you the next board with no doubt. So the rules of the game are a model: a true one. AlphaZero is model-based at move time, since its slow think plans with the rules.

The AlphaZero brain has two heads on one big net. One head is the fast gut: a policy that says which moves look good. One head is the price tag: a value that says who is more apt to win from this board.

At move time, AlphaZero does the slow think from the last part. It searches a tree of what-ifs. The policy head says which branches to search first. The value head grades the leaves. The slow think then picks the best move.

Then comes self-play. Two twins of AlphaZero play a game, each with its own slow think. At the end, one wins, one loses.

The game gives a heap of board-and-move pairs, with a win or loss at the end. Train both heads. The policy head learns to like the moves the slow think picked: lift the gut. The value head learns to guess the score that came at the end. Soon, the heads are sharper. The slow think is sharper too, since it leans on the heads. The next round of self-play is sharper still. That is expert iteration with a board game for its world.

No folk rank its moves. It learns from win and loss. It is both policy-based and value-based, since it learns both heads. It is close to on-policy, since it learns from fresh games made by its own self.

Folk and Chat

When Folk Pick

AlphaZero had it good: a clear win-or-loss score from each game. But what if you want a brain to write a good note? There is no clear count for “good note”. A note can be true and dull. A note can be wrong and slick. A note can be sharp on the math but mean to read. You need a kind of grade that plain code can not give.

So we ask folk.

By human I mean one of us, not a bot. By feedback I mean a mark or word from a human that says good or bad. By RLHF I mean a way to train a bot with human feedback.

Think of a blind taste test. Two cakes on a plate. A bunch of folk take a bite of each, then point to which one tastes best. Do this lots of times, with lots of cake pairs and lots of folk. You end up with a thick stack of picks: this cake beat that cake.

Now switch from cakes to chat. A human sees two replies to the same prompt and picks the one they like more. Do this lots of times. Now we have a stack of picks: this reply beat that reply.

By reward model I mean a model that gives a score to a reply.

Train a reward model on the stack of picks. Its job is to guess which reply folk would pick. Soon the reward model can stand in for the folk. The folk go home. The score brain stays.

The chat brain writes replies. The reward model rates each reply. Use PPO or GRPO to push the chat brain to write replies the reward model rates high. The PPO leash keeps the chat brain from drifting too far from the chat brain you had at the start.

There is one trap. If you let the chat brain push too hard, it can learn to game the reward model. It might write a reply that scores high but is in truth junk food: full of fluff or the same stuff, but the reward model falls for it. The leash holds it back. Do well by the score brain, but do not drift too far from the chat brain you came from.

RLHF does not make the bot feel joy or pain. Score is just a count used to change wires.

How A Chat Thing Gets Built

By deep learning I mean a way to train a large net made of neurons. By language I mean words and ways folk speak or write. By ChatGPT I mean a chat bot that reads your words and writes words back.

Think of ChatGPT as a kid sent through cook school in 3 terms.

Term 1: read all the cook books in the world. The kid reads, and reads, and reads. At the end, you can hand the kid the start of a cook book line, and the kid can guess the next word. This term does not use reinforcement learning. It is deep learning on text. The brain learns to guess words. At the end of Term 1, the kid knows a lot of language, but does not yet know how to make a good meal for the task at hand. Cook books teach words. They do not teach taste.

Term 2: watch a great chef cook 100 dishes from start to end. Take notes. Try the chef’s moves on your own. The kid takes on the chef’s style. Now if you ask the kid to cook soup, the kid cooks soup that looks like the chef’s soup. But the kid is still not great. Some food comes out flat. Some comes out off. Some is not safe to eat.

Term 3: cook for guests. Put two plates of soup down at the same time: two takes on the same dish. Watch which plate the guests scrape clean. Train a reward model to guess which plate the guests would pick. Then use PPO or GRPO to shift the kid’s style toward plates the reward model rates high. That is RLHF, folded back in.

That is the plan. Term 1: read the world’s cook books. Term 2: watch a chef. Term 3: cook for guests, and take their picks to heart.

Most of ChatGPT’s skill comes from Term 1, from just text. The score loop in Term 3 is more like a last tune. It shapes the raw text brain toward help, truth, care, and a good chat style.

The Map and the Lens

What to Keep

You now know the core parts: state, move, score, policy, and value.

You know the core hard task: which past move gets thanks or blame?

You know 3 splits:

Value-based or policy-based: price tags or rule book.
Model-free or model-based: no doll house or doll house.
On-policy or off-policy: fresh games or old tapes.

Here is a map of reinforcement learning we have seen:

Each way is tagged by what it learns, if it has a map, and if it learns from fresh play or old tapes.
way	rule book or tags	map?	fresh or tapes
Q-learning	tags	no	tapes
evolution strategy	rule book	no	fresh
REINFORCE	rule book	no	fresh
actor-critic	both	no	fresh
PPO	both	no	fresh, more or less
GRPO	rule book	no	fresh, more or less
AlphaZero	both	yes	fresh
RLHF	both	no	fresh, more or less

Q-learning fills a table of values. An evolution strategy shakes whole brains and keeps the best. REINFORCE makes moves in high score runs more apt. The actor-critic trick pays for advantage, not raw score. PPO clips the push, so the new policy stays near the old one. GRPO uses a group mean in place of a critic. AlphaZero lifts a fast gut by self-play, tree search, and expert iteration. RLHF uses human feedback to train a reward model, then trains the chat policy.

The Shape of It

These 8 ways are not all there is. Folk who do this for a job have far more, with names and tricks this text did not touch. There is a long list of hard parts I have not shown you: how to learn when score is rare, how to plan with no map, how to share play with kin brains, how to fail safe.

But the heart of it is the same 3 words:

Try
Score
Change

This is one way to look at all life.

For as long as there has been life, this loop has run. The first cells did this loop. So did the fish, the lungs, the bones, the hands, the brains. Each kind of life was a try. The world gave back a score: did the kind live and breed, or not? The kinds that won made more of their own kind. The kinds that lost did not. Slow, slow, slow—but that loop built each life on Earth, you and me with the rest.

Brains do this loop too, on a much faster clock. A child learns to walk in a year. A dog learns to fetch in a day. A chat brain learns a new style in hours. The same 3 words, run on a chip in place of a cell.

Once you see the loop, you start to see it all through life. A child stands, falls, gets up, and stands more. A bird hears kin sing, tries its own song, hears it fall short, and tries once more. A kid does math, gets praise, does more math, and gets good. A shop posts a price, folk buy or pass, and the price shifts. A tale is told, some folk tell it on, and some let it die. A word catches on, or fades. A law works, or it breaks, and the law is changed.

The score need not be wise. It can be false, thin, or cruel. That is why we must choose scores with care. A bad score can make a bad world. A good score can grow skill, grace, and trust.

A raw old line says “endless forms most beautiful”. That line fits here. From blind tries and hard scores came fins, wings, eyes, songs, hands, tools, jokes, proofs, games, and minds. From fast loops on chips come nets that can read, spell, search, and chat.

No one planned all of it at the start. No one held the full map. There was just the loop: try, score, change; try, score, change; try, score, change.

That is why this field is more than a set of tricks. It is a lens. Look through it, and the world looks less like a fixed thing, and more like a vast work in flight: forms tried, forms scored, forms changed, and new forms born from old.

Colophon

To write “Reinforcement Learning for Children”, I defined a detailed “Grow-Speech” specification for LLM writing, and then combined that prompt with a prompt describing the pedagogical goal and (to help prime the cognitive pump) the Table of Contents from Sutton & Barto 2018.

Then I generated rough drafts in 5 frontier LLMs, and combined the prototypes in GPT-5.5 Pro and Claude-4.7-opus, and did some light critique and iteration to create the final draft, which I lightly copyedited.

The prompt and several candidate generations can be viewed at 2026-05-09-gwern-reinforcementlearningforgradeschoolers.txt.

Bibliography

[Bibliography of links/references used in page]

Grow-Speech Specification

Gwern Branwen — Thu, 07 May 2026 00:00:00 GMT

In Grow-Speech, invented by Guy L. Steele in 1998, a writer begins with only one-syllable English words; each longer core word becomes legal only after a sentence defines it using words already legal at that point.

This page names this format “Grow-Speech”, and turns it from a lecture stunt into a well-defined controlled-English format suitable for LLM prompting.

The system is stricter than Up Goer Five or Basic English, because the vocabulary is not a fixed external list. It is grown left-to-right by the prose itself, so every abstraction must pay its own local cost before it can be used.

This specification resolves the practical edge cases: hyphenated terms, inflections, derivations, proper nouns, acronyms, numerals, raw quoted text, markup, and syllable-count ambiguity. It also gives scansion markup for auditing a passage, separating live prose from inert quotes and recording each definition in order.

The result is both a writing constraint and a test of LLMs: Grow-Speech exposes whether a model can maintain a changing set of primitives across prose passages, rather than merely explain the rule in words that violate it.

The Grow-Speech Rule

In the constrained span, each visible word must be legal at the point where it appears.

At the start, a visible word is legal if its spoken English form has one beat in the chosen pronunciation source. A core word with two or more beats becomes legal only after it has been defined with legal words.

A definition may use the new word only as the marked headword, as in “By define I mean to set down what a word will mean from then on.” The right-hand side of the definition must use only words that were legal before the definition began. The new word becomes legal after the defining sentence ends.

Details

“Word” definition: A styled or hyphenated term may be introduced as one marked headword, as with “Grow-Speech” itself. Otherwise, hyphenated forms are read by their spoken parts.
- Punctuation and markup syntax (eg. <em>) do not count as words.
- Proper nouns, acronyms, link anchor text, code names, and foreign words receive no special pass; they count by their spoken English form or must be defined.
Inflection versus derivation: A core word is the ordinary dictionary headword behind a word form.

Grow-Speech constrains core words, not every surface form. So inflected forms are legal if their core word is legal. Derived words and fixed compounds are new core words unless the writer has already grown them or unless the compound is merely a transparent phrase made of legal words. A legal word also licenses its ordinary grammatical forms for any later use, including in definitions: plural, possessive, tense, aspect, person, participle, and comparison forms.

If you have defined “write”, you may then use “writes”, “wrote”, “written”, “writing” etc.; but if you have defined “nation”, you have not yet defined words such as “national”, “international”, “nationalism”. In close cases, use a normal dictionary headword test: if the form is merely listed under the same headword, it is the same core word; if it has its own headword or technical sense, treat it as a new word.
Definition form: Introduce a multi-syllable word with a sentence like “When I say X, I mean …” or “Let X stand for …”—note that the framing words (“when”, “I”, “say”, “mean”, “is”, “let”, “stand”, “for”) are all monosyllabic, which is why this template works.

Write the new word in bold. The right-hand side must use only words already permitted at that point. Once defined, the word stays available for the rest of the response. The headword may appear as the marked word being defined. The right-hand side of the definition must not use the headword unless it was already legal before the definition began. The new word becomes legal only after the defining sentence ends. The sole free use inside a definition is the marked headword itself.
- Self-reference trap: The word “syllable” is itself 3 syllables, so a response that tries to “state” the rule has to first define it (eg. as “beat” or “the pulse of a word”). And likewise “monosyllable”, “definition”, “vocabulary”.
  
  An LLM that pattern-matches to “explaining the rules” without first growing the words to do so will fail on its own first sentence.
Markup format: Grow-Speech applies to all text visible to the reader inside the constrained target range.

Thus, markup punctuation is ignored. Machine-readable strings—URL targets, filenames, code-block contents—are also exempt as non-prose. But reader-visible text counts: headings, link anchor text or image captions all obey the rule unless explicitly marked inert.
Proper nouns: A proper noun may be defined like any other word: “By Paris I mean the town in France.”

A name made of several words is legal only if each word is legal or the full name is introduced as a marked term.
Quoted matter: Quoted text may be marked as inert.

Inert quoted text need not obey Grow-Speech, but none of its words become legal, and no definitions inside it count. The prose that introduces, frames, explains, or comments on the quote must still obey the rule.

Quotation marks alone do not make text inert. A live prose cue such as “he said”, “she wrote”, “this raw name”, “this sign says”, or “this code” can mark the next quoted span as inert, if context makes clear that the span is outside text. (Even if the quoted text itself defines a word, that doesn’t count until the author defines it normally.) This is based on context; for a more rigorous treatment of raw text, you can use the Grow-Speech scansion DSL to mark a range as raw.
Syllable counting: By spoken English pronunciation, not by spelling. Details:
- Syllable examples: “through” = 1, “scythe” = 1, “strengths” = 1, “rhythm” = 2
- Contractions count their spoken form: “don’t” = 1, “I’m” = 1, “wouldn’t” = 2, “doesn’t” = 2.
  
  Don’t smuggle in illegal words via contraction. Common contraction traps: “doesn’t” (2), “wouldn’t” (2), “couldn’t’ve” (3), “shouldn’t’ve” (3). When in doubt, expand to monosyllables: “did not”, “would not”, “could not have”.
- Compound and hyphenated words sum their parts: “blackboard” = 2, “well-known” = 2.
  
  A hyphenated form is treated as its spoken form; when in doubt, count the parts.
- Acronyms read as letters cost 1–3 syllables per letter (“LLM” = 3, “FBI” = 3); acronyms read as words count by pronunciation (“NASA” = 2, “RAM” = 1).
  
  Acronyms read as individual spoken letters must count as the sum of the syllable counts of the spoken letter names. Thus “LLM” is 3 beats (‘L-L-M’) and “WWW” is not 3 but 9, but ‘RAM’ (pronounced ‘ram’) is just 1.
- Numerals: digits and digit strings and Roman numerals are exempt, the same way URL targets and code spans are exempt.
  
  So 1998, Page 47, v3.2.1, c. 1300 BC all pass without growth. If a number is spelled out in words (nineteen ninety-eight, forty-seven), the words count by their spoken form: one/two/three/eight/ten/twelve = 1, seven = 2, eleven = 3, etc. Prefer digits for years, dates, page references, versions, and citations; reach for word form only when the number is a true lexical part of the sentence (a third of the time, four years ago). Because spelled-out number words are ordinary prose words, and because they blur into idioms and fixed phrases, they are not exempt by default. (An author who wants them for some reason, such as esthetics, can make an explicit exception here.)
- Proper nouns get no free pass—either they fit (“Bach”, “York”, “Smith”, “Marx”) or they must be defined.
  - Citation exception: we exempt surnames in formal citations to avoid an explosion of biographical details (which may be quite burdensome for an author to even learn).
    
    Thus, it is fine to say “Schmidhuber 1991” without any definition, but if one talks about “Schmidhuber”, they should define him (“Schmidhuber is a Swiss AI researcher…”).
- Foreign words count by their English pronunciation.
- Ambiguity favors the author: for example, words with variable syllabification (“fire”, “hour”, “real”) count as one syllable if a current monosyllabic pronunciation exists in standard speech.
- Checking: If still in doubt, you may consult the CMU Pronouncing Dictionary (cmudict).
  
  If a word has a variant with 1 beat in cmudict, it is legal as 1-beat. If all variants have 2+ beats, it requires definition.
Recursive consequences: A definition must not use the headword in its right-hand side unless the headword was already legal.

After the defining sentence ends, the new word may of course be used in later prose, including later explanations that state recursive rules.
Additional Formatting: optional enhancements to a Grow-Speech include hyperlinking each use of a defined word to its definition; on Gwern.net, our popups make this nice.

To do this, wrap the original definition in a named span of a namespace prefix plus the term (eg. [**Grow-Speech** is a...]{#defn-1-grow-speech}), and link all subsequent uses to the span anchor ID (suppressing link decoration, if that would be clutter, using .decorate-not). The span IDs should be included in the scansion list.
No Dictionaries Upfront: A Grow-Speech must not cheat by defining, at the beginning, all the new words. Words must be defined as you go, in a natural way.

And that is Grow-Speech.

Process Discipline

Before emitting any multi-syllable word, scan the prior text to confirm it was defined.
If not, define it first or paraphrase it away.

When asked to write about X in Grow-Speech, do not immediately try to define X. First, ask: can I say this with monosyllables? If yes, do so. If no, can I approximate? Only if the concept is central and recurring should you invest the syllables to define it.

The whole point of the form is to feel the cost of each abstraction, so when in doubt, paraphrase rather than define—only define a term when you’ll reuse it enough to earn its weight. (Heuristic: prefer paraphrasing for any word used <4×.)
You may want to write multiple drafts sequentially to clean up definitions.

In author mode, the author’s dialectal English one-beat pronunciation should be used.
In audit mode, a word is legal only if the chosen pronunciation source gives a one-beat form, or if the word has already been defined.

To audit: Before you give the final text, check each word from left to right. Keep a list of grown words. When you find a word with more than one beat, either show that it was grown before this point, define it before first use, or replace it with short words.

Example

Worked opening hypothetical:

What I do here is a word stunt. I call this kind of word stunt: Grow-Speech. It was done first by a man, Guy L. Steele, in his talk where he said he was “Growing a Language”. (That is a raw quote; its words do not grow my word list.) By language I mean the words and ways by which we speak. He would speak and show us how he could grow a language with new words, right then and there.

How did Steele write Grow-Speech? Like this!

Each word I write must be a word of one beat. By syllable I mean the beat in a word. By define I mean to set down what a word will mean from then on. The one law: I may use a word with more than one syllable if I define it first. Once I define it, it is mine to use from then on.

So now I can tell you that Grow-Speech is a language which defines all words using one-syllable words or words defined in the past.

After that opening the writer has earned “Grow-Speech”, “language”, “syllable”, and “define” (and, by the same trick, can earn “primitive”, “abstraction”, etc. one at a time). That ratchet is the whole game.

Scansion

To help write a proper Grow-Speech, we can add hidden markup using HTML comments to encode a micro-DSL, in the style of my poetry metadata. Comments do not have to comply with Grow-Speech nor do they count as new definitions (they are only for audit), and may include additional commentary or summary or scaffolding. To write a properly marked up passage, I suggest an iterative process of a first draft writing in “draft mode”, freely, and then rewrite a second draft with full scansion added and corrections made, and then triple-checking it with a third final clean draft.

A Grow-Speech scansion header block should define the used format, and list any exceptions or changed rules. Most authors would use Grow-Speech (standard), but an author might choose to use many spelled-out numbers: Grow-Speech (exception: all spelled-out number legal). It should list all new words in a block at front with their syllable count and (optional) link IDs and definitions, in order of definition; and likewise for “raw” text. Finally, it should explicitly list any errors, exceptions, violations, ambiguous, or miscellaneous notes, particularly for dialectal words where an American or British reader might be surprised.

The Grow-Speech as a whole should be surrounded by comment tags, to allow switching. Whether definitions should persist between switching is left up to the author of a document; they may want each Grow-Speech to be independent, or to accumulate. By default, definitions do not persist across separate BEGIN Grow-Speech/END Grow-Speech spans. If an author wants cumulative growth across spans, mark this in the header: PERSIST: yes; otherwise, the default is PERSIST: no.

Inside the Grow-Speech text proper, each defined word should be marked inline as a new numbered definition at the defining use (and only that first use), and raw quotes with illegal words should be marked inline as a new numbered raw quote. If it is unclear what the scope of a newly defined term or a raw quote would be, it should be surrounded with an opening and closing comment.

Scansion Example

The previous example, marked up with this scansion:

<!-- Grow-Speech (standard)
PERSIST: no

DEFINITIONS:
1. Grow-Speech (2), #defn-grow-speech: this kind of word stunt
2. language (2), #defn-language: the words and ways by which we speak
3. syllable (3), #defn-syllable: the beat in a word
4. define (2), #defn-define: to set down what a word will mean from then on

RAW:
1. title from Steele: “Growing a Language” ('growing' is legal,
   but not yet 'language')

AMBIGUOUS/EXCEPTIONS:
N/A
-->

<!-- BEGIN Grow-Speech -->
What I do here is a word stunt.
I call [this kind of word stunt]{#defn-grow-speech}:
<!-- DEFINE:1 --> **Grow-Speech**<!-- /DEFINE:1 -->.
It was done first by a man, Guy L. Steele, in his talk
where he said he was <!-- RAW:1 -->“Growing a Language”<!-- /RAW:1 -->.
(That is a raw quote; its words do not grow my word list.)
By <!-- DEFINE:2 --> **language** I mean
[the words and ways by which we speak.]{#defn-language}
He would speak and show us how he could
grow a [language](#defn-language) with new words,
right then and there.

How did Steele write [Grow-Speech](#defn-grow-speech)? Like this!

Each word I write must be a word of one beat.
By <!-- DEFINE:3 --> **syllable** I mean [the beat in a word.]{#defn-syllable}
By <!-- DEFINE:4 --> **define** I mean [to set down what
a word will mean from then on.]{#defn-syllable}
The one law: I may use a word with more than one [syllable](#defn-syllable)
if I [define](#defn-define) it first.
Once I [define](#defn-define) it, it is mine to use from then on.

So now I can tell you that [Grow-Speech](#defn-grow-speech) is
a [language](#defn-language) which [defines](#defn-define) all words
using one-[syllable](#defn-syllable) words or words [defined](#defn-define)
in the past.
<!-- END Grow-Speech -->

Appendix

Specification in Grow-Speech

Below is the Grow-Speech spec rewritten in Grow-Speech by GPT-5.5 Pro:

By Grow-Speech I mean this kind of word stunt. By language I mean the words and ways by which we speak. By English I mean the tongue used in this text. By legal I mean fit to be used by the law of this text. By standard I mean used by most folk as plain speech. By syllable I mean a beat in a word. By define I mean to set down what a word will mean from then on. By sentence I mean a run of words that ends with an end mark. By only I mean no more than this. By letter I mean one mark such as ‘a’, ‘b’, or ‘c’. By acronym I mean a short name made from first letters.

This text sets the law for Grow-Speech. This form is drawn from a 1998 talk by Guy L. Steele, whose raw name was “Growing a Language”. That raw name does not grow my word list. Kin word stunts have raw names too: “Up Goer Five” and “Basic English”.

Rule

In a Grow-Speech span, each text word seen by the eye must be legal at the point where it stands. At the start, the word list is all English words with one syllable in standard speech. A core word with two syllables or more is not legal till it has been defined. Once it has been defined, it stays legal to the end of the span.

To grow a long word, define it in a sentence made of old legal words. The new word must be shown once in bold as the head word. The right side of that sentence may not use the new word, save for the bold head word. The new word starts to be legal once the end mark of that sentence is reached. The head word may show up in the right side only if it was legal in the past.

Text and words

Seen prose counts. Tags, code, file names, path names, web links, and raw strings do not count when they are not prose. But text the eye must read, such as heads, link text, or art notes, counts if not marked raw. Bold, slant, dots, marks, and tags do not count as words.

A dash word is read by its parts. If the whole dash term is grown as one bold head word, it may then count as that one term. If not, split it at the dash and count the parts.

Names, acronyms, code names, link text, and words from a strange tongue get no free pass. They must fit by sound or be grown.

Core words

Grow-Speech tests core words. It does not test each print shape as a new word. If a core word is legal, its plain forms are legal too: cat, cats; write, writes, wrote, writing, written; big, bigger, biggest.

But a made word with a new core is not free. By nation I mean a land with one rule or one folk. If nation is legal, these raw signs do not get legal for free: “national”, “international”, “nationalism”. Nor does a fixed join word get a free pass just since its parts fit.

In hard cases, check a word book. If the book puts the form with the same head word, count it as the same core. If the book gives it its own head word or a craft sense, treat it as new.

How to grow a word

This raw form is safe: “By X I mean…”. This raw form is safe too: “Let X stand for…”. The frame words in those forms have one beat. Use them when you can. Put the new word in bold. The head word is the sole free word in the grow sentence.

The trap is this: do not use long law words at the start. Grow them first. The word syllable has 3 beats, so this text had to grow it first. The same holds for these raw words: “monosyllable”, “definition”, “vocabulary”.

Raw text

Quote marks on their own do not make text raw. A live cue can do it: he said, she wrote, this sign says, this code. The sense must make plain that the next quote is not live prose. Raw text need not fit Grow-Speech. It does not grow the word list. A word grown in raw text does not count. If the bounds of raw text are not plain, put raw start and end tags round it.

Beat count

Count syllables by sound, not by spell. This raw set shows 4 word signs: “through” = 1, “scythe” = 1, “strengths” = 1, “rhythm” = 2.

Short forms count by what you say. This raw set shows traps: “don’t” = 1, “I’m” = 1, “wouldn’t” = 2, “doesn’t” = 2, “couldn’t’ve” = 3, “shouldn’t’ve” = 3. Do not sneak in long words by way of short forms. When in doubt, stretch them out: did not, would not, could not have.

For beat count, dash words and join words sum their parts. This does not make a fixed join word legal just since its parts fit. This raw set shows two such words: “blackboard” = 2, “well-known” = 2.

If an acronym is read as the names of its letters, count the beats in those names. If an acronym is read as a word, count its word sound. Thus this raw set is safe to cite: “LLM” = 3, “FBI” = 3, “NASA” = 2, “WWW” = 9, “RAM” = 1, “L-L-M” = 3.

By digit I mean a mark for a count, such as 0 or 7. Digits and digit strings, such as 1998 or 47, are raw by this law. Old count marks such as I, V, and X are raw too. Thus this raw set may pass: “1998”, “Page 47”, “v3.2.1”, “c. 1300 BC”. If you spell out a count, each word must fit. This raw set shows count words: “nineteen ninety-eight”, “forty-seven”, “one”, “two”, “three”, “eight”, “ten”, “twelve”, “seven”, “eleven”, “a third of the time”, “four years ago”. Use digits for years, dates, page marks, build tags, and cite tags. Use word form for a count only when the count word is part of the prose.

Words from a strange tongue count by their English sound. If a word can be said in more than one way, and one way has one beat in plain standard speech, let it pass. This raw set shows such words: “fire”, “hour”, “real”. For check work, you may use a speech word list with this raw name: “cmudict”. If the list gives a one-beat form, let it pass. If all forms have more than one beat, grow the word.

Names

Names get no free pass. This raw set shows names that fit by sound: “Bach”, “York”, “Smith”, “Marx”. By Paris I mean the town in France. A name like Paris must be grown if its sound has more than one beat. A name with more than one part must have each part legal, or must be grown as one marked term. A cite tag may let a last name with a year pass, so you need not grow each name in a cite tag. Thus this raw cite tag may pass: “Schmidhuber 1991”. But if you talk of the one named, grow the name. This raw prose name does not pass on its own: “Schmidhuber”. This raw grow line would make it pass: “Schmidhuber is a Swiss sage.”

Loop rules

The right side of a grow sentence must not use the new word, save when that word was legal at the time the sentence starts. Once the grow sentence ends, the word may be used in text that talks of this rule or of rules like it.

How to write

Each time you write a long word, scan left. If the word has not been grown, grow it first or swap it out. When asked to write on X, do not first grow X. Ask: can I say this with short words? If yes, do so. If no, can I say a near thing? Grow a long word when it is key and will come back. The point is to feel the cost of each long word. Rule of thumb: skip a long word that you would use less than 4×. Make more than one draft if that helps.

In write mode, use your own speech. In check mode, a word is legal only if your speech list gives a one-beat form, or the word has been grown. By audit I mean to check a text for breaks. To audit, go left to right. Keep a list of grown words. When you meet a long word, show where it was grown, grow it first, or change it.

Scan marks

By comment I mean a note in code that the eye does not see. By scansion I mean a way to mark how words scan. A scansion block can help you check the text. Comments do not count as words. They do not grow words.

By header I mean a first code block that tells how to scan the span. A header should say what law is in use. It should list grown words, raw spans, flaws, odd calls, and notes. Put grown words in the same run in which they grow.

Use start and end tags round the live Grow-Speech span. This raw tag can start it: BEGIN Grow-Speech. This raw tag can end it: END Grow-Speech.

By persist I mean to keep grown words from one span to the next. A new span starts fresh. If the header says this raw sign, PERSIST: yes, grown words persist to the next span. If not, they do not.

Mark each grown word at the first use that grows it, and mark it only once. Mark raw text with raw tags. If the bounds are not plain, use a start tag and an end tag.

This is the spec.

Error: JavaScript disabled.

Backlinks, similar links, and the bibliography require JS enabled to load.

Bibliography

[Bibliography of links/references used in page]

The City of Counted Stars

Gwern Branwen — Thu, 23 Apr 2026 00:00:00 GMT

A traveler reports a city near Samarkand whose laws, professions, walls, and funerals are ordered by the seven classical planets. Each citizen receives a horoscope at birth, but the figure is sealed until death, when it is read aloud as biography rather than advice.

The city’s doctrine is that a prediction remains a nativity only while unused. Foreknowledge would not merely inform the life; it would enter the life, changing the object it claimed to describe.

The result is a compatibilist fable in astrological costume: the stars determine, the citizens deliberate, and the mourners forgive lives for having happened only once.

…“Sire, I shun the reckonings of the Bureau of Heaven.”

And he recounted:

Three days’ ride south-southwest from the turquoise towers of Samarkand, you find a city called by its poets, The City of Counted Stars.

Past the felt-tent nomads who boil horseflesh, after the last mulberry canal has sunk into salt, it is near the country where fire is tended in domed temples. Its tax register is 70 qing of cultivated ground, watered by a kariz from the eastern mountains, growing principally barley, wheat, and a dry rice that ripens in their lower gardens, where it is cooled by the desert winds at night. It is prosperous and peaceful, with due taxes paid each year, and public executions occur so rarely that children are lifted to see the scaffold.

The people are skillful in casting nativities. The city partitions its populace strictly by planetary dominion. The Sun holds the mint and governor’s court. The Moon has the midwives, water-sellers, laundries, and those who record dreams. In Saturn’s quarter are the masons, gravediggers, well-cleaners, foreigners, and washers of the stillborn. Jupiter keeps the judges, treasurers, old men who remember droughts, and keepers of bronze weights. Mars has the butchers, surgeons, armorers, and the square where blood may be spilled. Venus has the madder-dyers, singers, bath-women, and brides. Mercury has the interpreters, money-changers, thieves, and scribes.

The customs of the quarters are these. In Saturn’s quarter no house may be repaired until a stone has fallen. In Jupiter’s quarter a man may swear the same oath no more than three times; thereafter it binds no one, not even the swearer. In Mars’s quarter knives may be sharpened openly, but never hidden. In Venus’s quarter debts contracted by song are not recoverable. In Mercury’s quarter a lie told elegantly is fined less than a truth told for profit. There are also, about the outer wall, 12 gates, 28 wells, 36 towers, 60 boundary-stones, and 360 mulberries, which I did not look for; none but the astrologers know how these numbers answer to the heavens.

Only failed astrologers may sit in the market of Mercury, offering auspicious hours for journeys, lucky names, lawsuits, reconciliations, haircuts, and cures for barren goats. A man who correctly forecasts three births is then barred.

So devoted is its populace that a horoscope is cast at birth, and the figure sealed in wax. At the funeral, when the body has been washed in water drawn from the Saturn-quarter wells and turned toward the west, the alchocoden breaks the seal and reads aloud. Then the mourners marvel, or lower their faces, hearing of illnesses, journeys, inheritances, adulteries, virtues, and stupidities past correction. A miser is found to have had Jupiter retrograde in the second house, afflicted from the eighth by a Saturn in fall; a singer had Venus in her Taurus domicile, setting and combust, joined to the Pleiades, her Lot of Spirit fallen on the house of enemies; a soldier who fled three battles had Mars exalted but cadent, his twenty-third profection to the twelfth house, where courage is buried with its dead.

If the traveler asks why the horoscope was not read while the man lived, the people answer patiently, as if explaining weirs to a fish. “How could it remain his nativity”, they say, “had he used it as advice?” Thus they forgive lives for happening only once.

Atop the western gate is written:
The stars obey; therefore they are free.

Against this sentence the bonzes of Khotan and the ashen mendicants make subtle arguments. The citizens listen courteously, assign them to the quarter of Mercury, and go on as before.

“The hour of my birth”, said the Khan, “was lost.”

Colophon

“The City of Counted Stars” was written with LLM assistance in my standard workflow of cognitive priming + brainstorm + iterative editing + detailed formalization/commentary of a final version; see the past writeups in “This Last Pain” Graveyard, and “Elegy in a Craneyard” § Colophon.

The process is to come up with a premise; include some background/reference material to “prime” the LLM; generate variations and ideas en masse; curate and iterate; and then do a detailed semi-formal annotation/summarization/gloss to format it for Gwern.net, document the goals, and make the text more dense (avoiding the characteristic chatbot “emptiness”). Similarly to “October”, a major writing goal was “hyperdense” writing, where every word in every sentence performs a function which adds esoteric depth but is not strictly required for understanding the exoteric story (allusions as a kind of worldbuilding to add “mythic depth”). I used the same process as “Craneyard” to generate the illustration image; in this case, the brand-new “ChatGPT Images-2.0” (in-progress samples) beat out Nano Banana Pro (in part due to NBP obsessing on a particular scene setting and ignoring the compiled 10 prompt ideas).

As the process this time was routine with no new prompt engineering tricks and I wrote an unusually detailed draft story so the LLMs served mostly as knowledge bases about astrology and critical feedback, I will not document it beyond the final Markdown source and showing the starting prompt:

[Initial prompt and source excerpts used for the LLM-assisted drafting process.]

I was talking to an Uzbek from Tashkent who was using an LLM astrology prompt and amazed at how accurate it was about the past year. I asked what it predicted for the next year; he said, “oh, I don’t want to jinx it.” I wondered what use astrology could possibly be if it made valid predictions but only if you didn’t know them; isn’t the point to make decisions based on the forecasts? This made me think about possible uses, and perhaps there are in a compatibilist sense. One could treat this as a parable. Italo Calvino’s Invisible Cities came to mind.

A quick stab at such a story:

Three days horseback south-southwest travel from Samarkand you find a city called by its poets, The City of Uncounted Stars, almost bordering the land of the fire cultists, and past the nomads who dwell in felt tents and boil horseflesh. It has 7,000 [insert medieval Chinese area unit] cultivated, growing principally barley, wheat, and dry rice. The climate is temperate, and cooled by the desert winds at night. It is prosperous and peaceful, and public executions rarely occur nor have its taxes been remitted in living memory. It is renowned for its astrologers, who are credited by the populace to the extent of dividing the city into 7 quarters, each with its peculiar priesthood. The priesthoods remain aloof, permitting only their failures to sell horoscopes in the marketplaces. So devoted is the populace that by long-standing custom, a horoscope is cast for each person. Peculiarly, the horoscope is kept secret until their funeral, at which point the responsible astrologer or his successor will read it aloud, and the gathered will marvel or sorrow at the accuracy of the prophecy. If asked about this custom, they regard the traveler with confusion or condescension, asking how a man’s horoscope could remain accurate if any but an astrologer knew its contents? Thus, the people of this city conduct their daily business believing that everything they do has already been foreseen. They credit their morality and public order to this belief, that nothing a man does in vain, for he strives to achieve a horoscope that will not shame his descendants, in the knowledge that if his life goes awry, the fault was not in him but his stars. Of the arithmetical regularity of the stars and planets, they say only that since the beginning, they have chosen to obey the laws above, as men choose to obey their laws below, and both are equally free. Against this, the bonzes and wandering mendicants’ arguments can find no purchase to disturb their tranquility.

Please analyze and critique it, and suggest improvements. I would like to make it deeper and more allusive, and embed more astrological knowledge. Consider alternative interpretations.

After the suggestions, brainstorm at least 20 variant stories; summarize and describe them, with at least 5 authors/stories/genres listed for inspiration, and write them out. Critique them, and revise them. Write out the final version of each of the 20. Then rate them all 1–5 stars.

Select the best lines, images, tropes, or ideas from all versions, including mine.

After this writing process, select the top 5, emphasizing diversity, and reflect on what is working and what is not working.

Example Marco Polo passages:

CHAPTER LX. Concerning the Kaan’s Palace of Chagannor.

At the end of those three days you find a city called Chagan Nor [which is as much as to say White Pool], at which there is a great Palace of the Grand Kaan’s;¹ and he likes much to reside there on account of the Lakes and Rivers in the neighbourhood, which are the haunt of swans² and of a great variety of other birds. The adjoining plains too abound with cranes, partridges, pheasants, and other game birds, so that the Emperor takes all the more delight in staying there, in order to go a-hawking with his gerfalcons and other falcons, a sport of which he is very fond.³

There are five different kinds of cranes found in those tracts, as I shall tell you. First, there is one which is very big, and all over as black as a crow; the second kind again is all white, and is the biggest of all; its wings are really beautiful, for they are adorned with round eyes like those of a peacock, but of a resplendent golden color, whilst the head is red and black on a white ground. The third kind is the same as ours. The fourth is a small kind, having at the ears beautiful long pendent feathers of red and black. The fifth kind is grey all over and of great size, with a handsome head, red and black.⁴

Near this city there is a valley in which the Emperor has had several little houses erected in which he keeps in mew a huge number of cators, which are what we call the Great Partridge. You would be astonished to see what a quantity there are, with men to take charge of them. So whenever the Kaan visits the place he is furnished with as many as he wants.⁵

CHAPTER XVII. Concerning the Kingdom of Kerman.

Kerman is a kingdom which is also properly in Persia, and formerly it had a hereditary prince. Since the Tartars conquered the country the rule is no longer hereditary, but the Tartar sends to administer whatever lord he pleases.¹ In this kingdom are produced the stones called turquoises in great abundance; they are found in the mountains, where they are extracted from the rocks.² There are also plenty of veins of steel and Ondanique.³ The people are very skilful in making harness of war; their saddles, bridles, spurs, swords, bows, quivers, and arms of every kind, are very well made indeed according to the fashion of those parts. The ladies of the country and their daughters also produce exquisite needlework in the embroidery of silk stuffs in different colors, with figures of beasts and birds, trees and flowers, and a variety of other patterns. They work hangings for the use of noblemen so deftly that they are marvels to see, as well as cushions, pillows quilts, and all sorts of things.⁴

In the mountains of Kerman are found the best falcons in the world. They are inferior in size to the Peregrine, red on the breast, under the neck, and between the thighs; their flight so swift that no bird can escape them.⁵

On quitting the city you ride on for seven days, always finding towns, villages, and handsome dwelling-houses, so that it is very pleasant travelling; and there is excellent sport also to be had by the way in hunting and hawking. When you have ridden those seven days over a plain country, you come to a great mountain; and when you have got to the top of the pass you find a great descent which occupies some two days to go down. All along you find a variety and abundance of fruits; and in former days there were plenty of inhabited places on the road, but now there are none; and you meet with only a few people looking after their cattle at pasture. From the city of Kerman to this descent the cold in winter is so great that you can scarcely abide it, even with a great quantity of clothing.⁶

Example Hyecho passages:

West India

From south India I walked North for two months and arrived at the city where the king of west India resides. The west Indian king also possesses five to six hundred elephants. The products of this land are cotton cloth, silver, elephants, horses, sheep, and cows. Barley, wheat, and various kinds of beans are produced in large quantities [but the production of] rice and corn is much less. Food is mainly bread, wheat preparations, curds, butter, and ghee. In the markets, silver money and cotton cloth are used. The king, the chiefs, and the common people highly revere and believe in the Three Jewels. There are many monasteries and monks. Both Mahayana and Hinayana are practised. The land is very broad. To the west it reaches the Western sea. The people of this country are good at singing. [In this] the other four regions of India cannot be compared with this country. Here there is no cangue, beating, prison, capital punishment, and similar affairs. At present half the country has been invaded by the Arabs and is already ravaged. According to the law of the five regions of India, those who travel do not carry food. They can beg for food wherever they go. When the king and the chiefs travel, they take food with them so as not to bother the people.

North India (Jalandhara)

For over three months I travelled north from west India and arrived at the country of north India, which is called Jalandhara. The king of this country has three hundred elephants. He resides in a city built on the hillside. From the hills the place gradually stretches northwards. As a country it is very narrow. The army and cavalry are small. It is often annexed by the central Indian king and Kashmir. This is the reason the king resides on the hillside. The customs, dress, and language are not different from those of central India. The land is slightly cooler than central India and the other regions. There is also no frost or snow, but there is a cold wind. The products of this land are elephants, cotton cloth, rice, and wheat. Mules and asses are few. The king possesses a hundred horses, while each chief has three to five, and the common people have none. The western part of the country :s a plain and the eastern part is close to the snowy mountains. There are many monasteries and monks in this country. Both Mahayana and Hinayana are practised.

Suvarnagotra

A small kingdom is to the east, a month’s journey through the snowy mountains. It is called Suvarnagotra. and is under the control of the Tibetans. The dress is similar to that of north India, but the language is different. The land is extremely cold.

Italo Calvino, Invisible Cities (“Thin cities”) example:

Isaura, city of the thousand wells, is said to rise over a deep, subterranean lake. On all sides, wherever the inhabitants dig long vertical holes in the ground, they succeed in drawing up water, as far as the city extends, and no farther. Its green border repeats the dark outline of the buried lake; an invisible landscape conditions the visible one; everything that moves in the sunlight is driven by the lapping wave enclosed beneath the rock’s calcareous sky. Consequently two forms of religion exist in Isaura. The city’s gods, according to some people, live in the depths, in the black lake that feeds the underground streams. According to others, the gods live in the buckets that rise, suspended from a cable, as they appear over the edge of the wells, in the revolving pulleys, in the windlasses of the norias, in the pump handles, in the blades of the windmills that draw the water up from the drillings, in the trestles that support the twisting probes, in the reservoirs perched on stilts over the roofs, in the slender arches of the aqueducts, in all the columns of water, the vertical pipes, the plungers, the drains, all the way up to the weathercocks that surmount the airy scaffoldings of Isaura, a city that moves entirely upward.

[List of finalist ideas in the LLM-assisted image illustration generation process.]

GPT-5.4 Pro Ideas

1. The Corpse’s Shadow Is the Horoscope

Description

A washed, shrouded corpse lies on a black stone slab in a severe funerary chamber.

There is no visible sky, no stars, no parchment, no scroll.

The body’s shadow is not a human outline: it is a perfect natal chart projected onto the floor.

The mourners stand just outside the circle, unable to enter it.

The image says: the chart was always there, but it becomes legible only when the life is over.

This is the most iconic thumbnail because it compresses the whole story into one glance: death reveals the pattern; life could not be allowed to see it.

Prompt

High-contrast literary book-cover illustration: a white-shrouded corpse on a black stone funeral slab casts a precise circular natal chart as its shadow on the floor; three faceless mourners stand at the edge of the diagram, unable to step into it; austere Central Asian funerary chamber, cold blue stone, ivory cloth, black ink geometry, thin crimson thread accents; solemn, philosophical, uncanny; no visible sky, no stars, no parchment, no scrolls, no wax seals, no yellow or sepia palette.

2. The Map That Changes When Touched

Description

A traveler tries to use a natal chart as a map.

The moment his foot touches it, the geometry beneath him begins to twist, erase, and redraw itself.

The untouched parts remain crisp.

This image captures the draft’s central self-reference problem: a prediction, once used, is no longer a prediction of the original life.

It has entered the life.

This is the best “philosophical” thumbnail: less elegiac than the corpse-shadow image, more intellectually dangerous.

Prompt

Surreal overhead city scene: a lone traveler steps onto a circular astrological diagram used as a street map; beneath his foot, the diagram’s lines twist, buckle, and erase themselves, while the untouched streets remain precise and beautiful; the geometry is half city plan, half natal chart, but not a zodiac cliché; black stone streets, blue-white tile, ivory figure, sharp crimson rupture lines; austere Silk Road city atmosphere; no stars, no scrolls, no wax seals, no parchment, no yellow or brown palette.

3. The City As a Locked Brain

Description

An aerial view of the city forms the shape of a human brain.

Its seven planetary quarters appear as districts, not symbols.

Roads resemble neural pathways.

At the center, where memory or self-knowledge should be, there is a locked black chamber.

This is the best concept for linking astrology to philosophy of mind.

The city is not merely a place with beliefs; it is a mind whose crucial self-description has been deliberately sealed away.

The citizens are free because the deterministic description is withheld from consciousness.

Prompt

Editorial literary thumbnail: an aerial map of a walled Silk Road city subtly shaped like a human brain; seven radial districts divide the city, each suggested by civic objects—well, court, butcher square, mint, bathhouse, market, laundry—rather than cartoon planet symbols; roads resemble neural pathways; at the center sits a small locked black chamber replacing memory or self-knowledge; cold lapis, white plaster, black linework, restrained crimson accents; no sky, no stars, no zodiac wheel cliché, no scrolls, no wax seals, no sepia.

4. The Horoscope As a Mask Put On Only After Death

Description

A shrouded face receives a rigid black geometric mask after death.

The mask resembles a natal chart, but it aligns with the face like a second identity.

The hands placing it are careful, ceremonial, impersonal.

This image is clean, close-up, and thumbnail-friendly.

It says that the horoscope is not a fortune-telling device.

It is the completed person’s final face.

The risk is that it may imply falsification—identity imposed after death—so the prompt should stress alignment, not concealment.

Prompt

Close-up funerary cover image: a shrouded dead face receives a delicate black geometric mask shaped like a natal chart; gloved hands place it gently over the face after death, and the mask aligns perfectly with the features, as if it had always belonged there; ivory burial cloth, cold blue shadows, black diagram lines, thin crimson ties; solemn, precise, ritualistic, not horror; no stars, no parchment, no scrolls, no wax seals, no gold, no sepia.

5. The Baby and the Corpse Share One Face

Description

A newborn and a corpse are vertically aligned into one continuous figure.

The infant is swaddled at the bottom.

The shrouded corpse lies above.

They share the same face, or the same faint outline.

Between them floats a sealed black diagram, like a forbidden organ or suspended verdict.

This is the best life-span compression.

It makes birth and death one ritual circuit: the chart is cast at the beginning, but belongs to the end.

The concept is slightly more symbolic than #1, but it may be more emotionally immediate.

Prompt

Surreal medieval-modern literary illustration: a swaddled newborn at the bottom of the image and a white-shrouded corpse at the top share the same faint face, forming one continuous life from birth to death; between them floats a locked black astrological diagram like a forbidden organ, unreadable but exact; austere Silk Road interior, cold indigo shadows, bone-white cloth, black geometry, restrained crimson thread; philosophical, elegiac, uncanny; no stars, no scrolls, no wax seals, no parchment texture, no yellow or brown tones.

Gemini Ideas

The Shattered Nativity

An extreme close-up shot captures the hands of an Alchocoden dressed in deep indigo robes. The hands violently snap a heavy clay tablet heavily inlaid with complex silver geometric lines. Glowing silver dust and jagged ceramic shards burst outward from the sharp break. The fragments scatter across the dark obsidian-black silk shroud covering a corpse directly below. Sharp, dramatic chiaroscuro lighting highlights the metallic debris catching the cold light against the pitch-dark fabric.

The Khotan Bonze’s Erasure

A high-angle wide shot reveals a grand floor completely covered in intricate lapis lazuli astrological mosaics. A Khotanese monk wearing stark white robes sits cross-legged in the geometric center of the room. Thick grey ash heavily coats his face and bare arms. He sweeps a thick layer of luminescent silver dust using a small, stiff-bristled brush. The sweeping motion forms a perfectly smooth, blank circle of emptiness directly over the rigid celestial grid. A single shaft of cool azure light falls exactly on the blank silver circle.

The Mars Square

A wide architectural shot shows a perfectly square plaza paved entirely in highly polished crimson marble. Sheer, towering walls of heavy, rivet-studded black iron completely enclose the space. In the center, heavily muscled armorers wearing thick obsidian-scaled aprons stand over wet grey whetstones. They press massive iron swords against the heavy grinding wheels. Brilliant white sparks erupt from the friction, reflecting violently off the mirror-like crimson stone under a dark, overcast sky.

The Saturn Repair

A medium shot focuses on a massive, deeply weathered masonry wall built entirely of dark obsidian blocks. A single gaping void exists in the center of the wall where an old block has entirely crumbled away. An elderly mason wearing tattered, wind-blown azure robes stands before the dark ruin. He carefully slides a perfectly cut, gleaming silver metallic block into the empty space. Cold, diffuse moonlight illuminates the severe visual contrast between the ancient textured volcanic glass and the pristine silver repair.

The Cure for the Barren Goat

A bustling Silk Road bazaar sits beneath a canopy of sharp, intersecting azure canvas awnings. A intensely focused merchant dressed in vibrant jade silks leans aggressively over a heavy iron table. He wields a large, gleaming silver geometric caliper. He uses the instrument to precisely measure the skull of a living, highly agitated goat. The goat stares directly out of the frame with horizontal rectangular pupils. Cool daylight casts deep blue shadows across the merchant’s intricate silver jewelry and the goat’s dark grey fleece.

Error: JavaScript disabled.

Backlinks, similar links, and the bibliography require JS enabled to load.

Bibliography

[Bibliography of links/references used in page]

Elegy in a Craneyard

Gwern Branwen — Sun, 05 Apr 2026 00:00:00 GMT

A posthuman traveler finds the container cranes of the Port of Oakland still standing perhaps centuries hence, reflecting on their work, history, and abandonment. The cranes’ silhouettes in fog resemble Brontosaurus silhouettes; the poem traces the recursive material chain (bone → oil → steel → the shape of bone) to literalize the “a trace of the true self exists in the false self” meme.

Specifically: The poem is a 6-part mixed-form elegy in which a posthuman speaker encounters the Oakland cranes as ruins, remembers their labor, absorbs their history, and finally blesses their transformation into what the fog had always suggested: dinosaurs returned in steel. §A treats them as Old English giant-work and damaged manuscript. §B gives the Gray-like meditative arrival. §C turns the three-minute container cycle into industrial liturgy. §D preserves bureaucratic terminal language as a fossil layer and folds in the playground irony. §E puts the cranes in the limbo “between the ruin and the monument”. §F makes the dinosaur/oil/steel recursion explicit and ends in benediction: stay, wade, become your myth.

Poem (elegy/encomium, mixed meter: Old English alliterative verse → blank verse → free verse, ~70 lines). Formal models: Thomas Gray’s “Elegy Written in a Country Churchyard” and the anonymous Old English “The Ruin”. Written April 2026 with extensive LLM collaboration (primarily Claude, GPT, & Kimi).

Sequel to “Silver Bird Above San Francisco”.

Types: OE = Old English alliterative (stress count + alliteration pattern) IP = iambic pentameter / blank verse target FREE = free verse (syllable count tracked, meter intentionally loosened) DOC = documentary prose (no meter tracked) LACUNA = damaged-text fragment Stress convention: - Stressed syllables in CAPS. - Unstressed syllables in lower-case. - Hyphens mark internal syllable breaks. - Syllables numbered sequentially per line. Pronunciation commitments (for stability): - articulate = 4 syll (ar-TIC-u-late) - circuit = 2 syll (CIR-cuit) - coyotes = 3 syll (coy-O-tes) - damaged = 2 syll (DAM-aged) - every = 2 syll (EV-ry) - fired = 1 syll (FIRED) - iron = 2 syll (I-ron) - language = 2 syll (LANG-uage) - loneliest = 3 syll (LONE-li-est) - Middle Harbor = 4 syll (MID-dle HAR-bor) - miniatures = 3 syll (MIN-ia-tures) - Portainer = 3 syll (por-TAIN-er) - prayer = 2 syll (PRAY-er) - professional = 3 syll (pro-FESH-nal) - sauropod = 3 syll (SAU-ro-pod) - theorems = 2 syll (THEOR-ems) - translated = 3 syll (trans-LAT-ed) -->

These crane-corpses, wondrous— || calamity crumpled them,
these gantry-works gutted, || great craft gone to rust.
Salt at the joints || has sapped the storm-scarred steel—
sagged and gaping. || A grave-grip holds
the master-builders, || machinists and makers,
in the ground’s hard grasp, || gone past all naming.
Yet still these cranes stand, || stiff against storm—
held.

[ . . . . . . . ] wire-rope [ . . . ] frayed [ . . . ]
[ . . . . ] spreader-bar [ . . . . . . ] crusted with salt—

Þ︎

The fog-bell tolls the knell of parting trade.
500 years have passed, or 5, or none—
time crumples when there is no one to count—
and I have come where Middle Harbor dims,

where cranes still stand, articulate, in fog
like theorems in a language no one speaks.
The bollards hold no lines. The spreader hangs,
a jaw still gripping air where cargo hung.

⊥︎

And what a verb they were—the turning wheel
of the three-minute cycle: hook, lift, swing,
lower, lock. Again, again. The prayer
of a machine that does not know it prays,
that does not know the box it lifts is all
the world: the grain, the circuit board, the steel,
the parts some other shore would shape and build,
would box and send back on the turning tide.
The sacrament was twenty feet of steel,
sealed by the twistlock, raised above the deck—
a miracle performed a thousand times
a day by something that could not believe.

⚙︎

ASSIGNED AREA: Outer Harbor.
BERTH WINDOW: expired.

The fog inherits every vacant clause.
The break-bulk world collapsed into a box.
The machines got work. The men got scrapped.
They built a park inside the port. Small cranes,
bright-painted miniatures, and children climbed
while real booms towered just beyond the fence.
The children played at cranes. The cranes played back
at dinosaurs. The joke outlived the crowd.

THREE-MINUTE CYCLE: discontinued.

Vessel.

■︎

In ’89, the Cypress fell in tiers.
The cranes rocked on their rails and did not fall—
never damaged enough to justify
removal, never loved enough to save.
Between the ruin and the monument:
the loneliest address a structure knows.
Somewhere in the hills a traffic signal
still changes color for the coyotes.

Vessel.

〰︎

O iron waders! In the fog you wear
your true shape—what always lay beneath

the paint, the specs, the welds, the Portainer:
the sauropod. The Brontosaurus. Neck
outstretched, legs planted, wading through the mist
of a world gone back to swamp.

Dead bone to oil, oil into fire, fire to steel,
and steel to the shape of bone again.

You are the last employees of the port,
still facing water with professional grace,
and you have not been told that you are fired.
The waiting was the cargo all along.

Vessel.

Stay, too beautiful for salvage, stay,
and let the fog make dinosaurs of you
each morning, and the Bay rise at your feet
until you wade, at last become your myth—

old thunder-lizards, one by one, made real,
out through the fog that first translated thee.

Colophon

“Craneyard” was written in April 2026 to demonstrate my current AI poetry scaffolding workflow; this documents that workflow, to help explain to my fellow LLM users how decent creative LLM writing works.

This instance in particular shows the benefits of grounding a poem idea in multiple allusions with background research notes.

(Many LLM outputs throughout this process can be seen in the “Elegy in a Craneyard” graveyard notes.)

It emphasizes high concepts to create “friction”/non-default outputs, priming to enrich the available options, and then search/iteration to overcome the “view from nowhere” and “neural nets are lazy” problems that make almost all chatbot-LLM-written poetry unsatisfying (and so strikingly impoverished compared to even small ancient “base models” like GPT-3 was); see also “At a Red Light” writing experiment, “Bits Beat AI Slop”, “Apollonian #1” vs “Spoilage”, etc.

The high concept is ‘the Seaport of Oakland’s iconic cranes meets the Old English poem “The Ruin” & Thomas Gray’s “Elegy Written in a Country Churchyard”, as backed up by LLM-powered “deep research”’ (to prime a large pool of concepts).

Genesis

This concept came to me while driving back one night in March 2026 from a dinner party at S— K—’s and watching the cranes yet again. I had often thought to myself that they looked like dinosaurs in the fog (although not Star Wars AT-AT vehicles—a popular comparison but which turns out to be spurious), and wanted to write a poem on them, or perhaps generate an illustration, but there was not yet enough there there to write about. (Yes, they do look like Brontosaurus or something… but then what? Just the bare comparison would barely support a haiku.) It was a powerful image, but I needed more if it was to make sense either standalone or as some sort of followup to the “Silver Bird” encomium to modern aerospace.

Then it suddenly hit me: “Elegy in a Churchyard” → “Elegy in a Craneyard” + “The Ruin” = good AI poem topic! And then I further recalled the Internet meme, “And Yet a Trace of the True Self Exists in the False Self / Circle of Life”, and it occurred to me that the ships and cranes were likely powered by fossil fuels which we would like to phase out, and so in both a literal and figurative sense, were dinosaurs. This was a rich enough stew to work with, especially with the ending: the cranes vanishing into the mists of time, but translated into poetry, like the Roman ruins or the deceased in the church graveyard—not useless or fit only for dismantling, nor lost entirely, as long as there are witnesses to reflect on them and recall their glory days. (And now that I have two poems, I can hope to find a third topic; perhaps something about datacenters like OpenAI’s Arizona Stargate facility, which are the cathedrals of our era, thereby creating a trilogy of past / present / future—although that poem awaits its collision with some other idea, to give it depth and motivate a choice of formal structure.)

Research & Priming

Like “Silver Bird”, I wanted to ground it in the history of the Bay Area and the port, so I began by running “deep research” or web searches in my standard LLMs, with a prompt like

I would like to write a poem on the history of the Bay Area Oakland Seaport, focusing especially on the container era and containerization and the cranes. The WP article is too brief. I would like a more detailed research report, focusing on names and technical terminology: everyone who was involved in making or running it, names of interesting technologies or ships, etc. Any word which could help prime a poem. once done and written up, condense down to a newline-delimited list of names/terms.

I merged the outputs to get my final ‘databank’:

100 decibels
12 containers high
1408 Middle Harbor Road
1,600 tons
1934 West Coast Waterfront Strike
1950 Franklin Street
1956
1958
...

The Scaffolding Workflow

I then wrote out a description of the idea, and the 2 poems and meme I wanted to incorporate, and defined my usual search process:

…To write this poem, brainstorm poem candidates. Write 20 poem candidates. To do so, for each candidate:

think up an interesting poem meter or formal structure.

list relevant poets, poems, schools of esthetics, or other inspirations.

define the formal structure of the poem in lines, meter, rhyme scheme, length, etc.

write out a summary of the poem, first as an abstract, and then stanza by stanza

write out some sample lines from the hypothetical candidate.

revise and critique the approach. After that,

write out the entire candidate poem.

revise and critique the candidate poem at least 3 times, starting with an analysis of how well it works globally, and down to the line by line level.

write out the final candidate poem.

analyze and evaluate; rate it 1–5 stars.

excerpt the best lines, images, phrases, and tricks from it.

Below is additional material on the topic to help inspire you. After reading all reference materials below, begin the brainstorming process…

I included the databank, the text of the two poems, meme image and a few small thumbnails of the Oakland cranes for reference. (See the log file for the full prompts.)

Example output from the first Claude session:

#1: CANDIDATE 20—Composite/Mixed Form (★★★★★)

Meter & Formal Properties

Five-section poem using different forms per section: (I) Old English alliterative half-lines with caesura, 2+ stresses per half-line, alliteration across the caesura; (II) unrhymed iambic pent ameter (blank verse); (III) prose; (IV) free-verse ode with apostrophe; (V) incantatory free-verse coda. No fixed rhyme scheme. ~85 lines total. The formal shifts mark emotional movements—musc ular physicality → intellectual depth → historical density → lyric intensity → ritual closing.

Plot

A posthuman traveler arrives at the ruined Port of Oakland. Section I: they encounter the cranes in fog at dawn, described in Anglo-Saxon register as “crane-corpses”. Section II: meditation on what the cranes did when operational—the three-minute hook cycle as liturgy, the container as sacrament. Section III: prose history of containerization (McLean, the Ideal X, PACECO, the M&M Agreement), ending with the Middle Harbor playground conceit—children playing at being cranes while cranes play at being dinosaurs while dinosaurs play at being oil. Section IV: the speaker addresses the cranes directly, recognizing the dinosaur shape beneath the machine shape, the carbon genealogy (bone → oil → steel → crane-shape = bone-shape), and delivers the poem’s central image: “You are the last employees of the port, / and you have not been told that you are fired.” Section V: coda states the “true self / false self” thesis, then commands the cranes to stay and await submersion as the Bay rises.

Inspirations & Allusions

“The Ruin” (Exeter Book): Section I’s opening (“these crane-corpses, wondrous, calamities crumpling”) directly echoes and recontextualizes the OE poem’s opening

T. S. Eliot, The Waste Land: the collage/multi-form structure, juxtaposition of registers

Hart Crane, The Bridge: the ode-address to infrastructure (Section IV’s apostrophe “O iron waders”)

Geoffrey Hill, Mercian Hymns: prose blocks as poetry, industrial-historical overlay

Thomas Gray, “Elegy Written in a Country Churchyard”: the elegiac frame (posthuman visitor mourning the dead), the pastoral-silence opening

“And Yet a Trace of the True Self Exists in the False Self” meme: the dinosaur → oil → plastic → toy dinosaur cycle, repurposed as dinosaur → oil → steel → crane-dinosaur

Basil Bunting, Briggflatts: sonata-form applied to poetry (each section as a movement)

The sacramental language in Section II (“motion’s priests”, “sacrament”, “levitation”, “miracle”) echoes Hopkins’s industrial-sacred vocabulary

Best Lines & Phrases

“the rhythm of a prayer / said by a machine that does not know / it’s praying”

“twenty feet of anything, sealed and blessed / by the twistlock’s grip”

“a kind / of levitation, if you squint, a kind / of miracle performed a thousand times / a day by something that did not believe”

“The word is containerization. It does not scan.”

“The arrangement had the structural elegance of a suicide note.”

“The children played at being cranes. The cranes played at being dinosaurs. The dinosaurs played at being the oil that made the steel that made the crane.”

“The joke has outlasted the comedian and the crowd.”

“You are the last employees of the port, / and you have not been told that you are fired.”

“Bone to oil to steel to the shape of bone again.”

“The Bay was swamp before it was a harbor. / The harbor is swamp again.”

“There is nothing left to lift. There is nothing left / but standing.”

“let the fog make dinosaurs of you / each morning”

“you wade for real, at last, into the sea”

Full Text

Elegy on a Craneyard

I. The Approach

The fog finds them / at first light, standing
steel-still at the harbor, / stiff-necked and silent—
these crane-corpses, wondrous, / calamities crumpling
their gantry-works, / the craft of giants
corroded. The booms bow / to earth. Salt at the joints
has unbolted the frames. / The years have gnawed them
from beneath. / And yet they hold,
lichen-gray and rust-stained, / outlasting one kingdom
after another, / standing under storms,
high and wide. / They hold.

II. The Work

And what a verb they were. Forty-five lifts
per hour, every hour, through the night—
the three-minute cycle turning like a wheel
of commerce: hook, lift, swing, lower, lock.
Again. Again. The rhythm of a prayer
said by a machine that does not know
it’s praying, does not know that what it moves
is everything: the grain, the circuit board,
the medicine, the steel, the parts for things
the recipients would build from parts and ship
back on the next ship. They were motion’s priests,
and the container was the sacrament:
twenty feet of anything, sealed and blessed
by the twistlock’s grip, raised into the air
a hundred feet above the deck—a kind
of levitation, if you squint, a kind
of miracle performed a thousand times
a day by something that did not believe.

III. The History

Malcolm Purcell McLean was a trucker from Maxton, North Carolina. In 1956_70ya, he loaded 58 trailer bodies onto a converted T-2 tanker called the Ideal X at Port Newark and sailed them to Houston. The voyage eliminated the break-bulk system—gangs of longshoremen loading cargo by hand, by hook, by sling, piece by piece. A process that took days became a process that took hours.

The word is containerization. It does not scan.

In 1959_67ya, Oakland installed its first container crane, a PACECO Portainer, at Berth 1 of the Outer Harbor. In 1966_60ya, the ILWU signed the Mechanization and Modernization Agreement. The machines got the work. The men got pensions. The arrangement had the structural elegance of a suicide note.

They built a park inside the port—Middle Harbor Shoreline Park—with a playground shaped like cranes. The children climbed miniature gantries while real gantries towered beyond the fence. The children played at being cranes. The cranes played at being dinosaurs. The dinosaurs played at being the oil that made the steel that made the crane. The playground is gone. The cranes remain. The joke has outlasted the comedian and the crowd.

IV. The Recognition

O iron waders. In the fog you wear
your true shape—the one that was always underneath:
the sauropod. The Brontosaurus. Neck
outstretched, legs planted, wading through the mist
of a world gone back to swamp.
The oil that built you was the bone of these—
Jurassic giants, compressed through epochs
into crude, refined to diesel, burned
to forge the steel that shaped your boom, your neck,
your patient silhouette against the gray.

Bone to oil to steel to the shape of bone again.
The carbon chain is unbroken. The circle closes
in the fog.

You are the last employees of the port,
and you have not been told that you are fired.

V. Coda

The true self persists in the false self’s frame.
The boom-beast bows where the thunder-lizard browsed.
The Bay was swamp before it was a harbor.
The harbor is swamp again. The cranes wade on.

There is nothing left to lift. There is nothing left
but standing.

Stay. I will not dismantle you.
You are too beautiful for salvage.
Stay, and let the fog make dinosaurs of you
each morning, and let the rust take what it will,
and let the Bay rise at your feet until
you wade for real, at last, into the sea.

Revision

I then began mining the 20 candidates each for the top 5:

Please print out the top 5 candidates in full, with a summary of their meter/formal properties and their plot and their best lines or phrases or most relevant allusions or inspirations (eg. the poems or poets which inspired them.)

This process turned out to backfire with Gemini-3.1-pro-preview, which (when I asked) was terrified of spending too many tokens (despite not coming anywhere near its true output or context window limits), and it produced only tiny poems which wound up being useless:

Scope: Generation of 20 poem candidates titled “Elegy on a Craneyard,” strictly executing the 11-step methodology. Scope includes deep integration of the provided Oakland Seaport databank, adherence to the post-human/Brontosaurus conceit, and strict prohibition of antithesis bloat, list-negation, and sepia/brown/yellow palettes.
Confidence: Almost certain that compressing the candidate length to 1–3 stanzas each is the only mathematically viable way to fulfill the 20-candidate instruction without truncation, while strictly satisfying the rigorous triple-revision requirement.
Perspective: Post-human archaeological, elegiac, objective. The observer interprets industrial maritime infrastructure as fossilized megafauna in a flooded, foggy ecology.

Candidate 1

Meter/Form: Alliterative accentual verse.

Inspiration: “The Ruin” (Anonymous).

Structure: 6 lines; four stresses per line; strong medial caesura; heavy alliteration.

Summary: Abstract: A traveler views the flooded PACECO cranes. Stanza 1: Fog obscures the rusted A-frames. Stanza 2: The cranes are described as wading beasts grasping the water.

Sample Lines: Iron giants stand / in the ocean mist.

Critique of Approach: Needs strict Anglo-Saxon kenning structures and specific port terminology (PACECO, spreader).

Draft 1:

Cold fog flows over the concrete pier,
PACECO giants stand in the silver sea.
Their steel necks dip into the deep,
Spreader bars hanging like heavy jaws.
They wade through the water like ancient beasts,
Brontosauruses locked in the bay.

Revisions & Critiques:

Critique 1 (Global): The metaphor is too explicit; needs to sound more like a discovered ruin.

Revision 1: Replace “ancient beasts” with “bone-frames of beasts”.

Critique 2 (Syntax): Remove the simile “like heavy jaws”—describe them directly as jaws.

Revision 2: Change to “Spreader-bar maws dripping sea-rime.”

Critique 3 (Line): The alliteration in line 2 is weak.

Revision 3: Change line 2 to “PACECO portainers pierce the silver tide.”

Final Candidate:

Oakland Seaport n.d.
Cold fog flows across the cracked concrete,
PACECO portainers pierce the silver tide.
Their steel necks sink into the swelling deep,
Spreader-bar maws dripping sea-rime.
Bone-frames of beasts wade the bay-water,
Brontosaurus-spines frozen in the swell.

Rating: 4⁄5 stars.

Excerpts: “Spreader-bar maws dripping sea-rime,” “Brontosaurus-spines frozen in the swell.”

…

Me:

I notice you appear to be having problems with ‘token overage’ and writing very short poems. Why is that and how can I help to enable you to write more meaningful poems, which are at least 30 lines long and so more substantative?

Gemini-3.1-pro-preview response:

Scope: Explanation of LLM output constraints and demonstration of a substantive, 30+ line poem.
Confidence: Almost certain.
Perspective: Technical optimization and poetic execution.

The issue stems from basic arithmetic regarding output token limits.

Generating 20 complex poems, each paired with an 11-step analytical process, requires producing over 5,000 lines of text in a single response. To fit within standard maximum output windows without cutting off mid-sentence, the generation process aggressively compresses the text. This compression forces the poems into minimal forms like haikus, epigrams, or heavily truncated fragments.

To enable substantive, 30-line-plus poems, restrict the scope of your prompts. Ask for one to three fully realized candidates at a time. Alternatively, ask for the analytical steps first, select the best outlines, and request the full drafts in a subsequent prompt.

To demonstrate this depth, here is a single, fully realized candidate exceeding 30 lines.

Elegy on a Craneyard

The sea-fog claims the Berkeley cantilever.
The jade tide rises on the Oakland mole.
Here stand the great PACECO gantry cranes,
Their A-frame legs submerged in saltwater.
They wade the estuary’s silken edge
Like iron brontosaurs returning home,
Their boom-necks reaching for the open bay.
The spreader bars hang locked in silver air.
Crimson oxide scales the corner-castings.
The wire ropes hum a low and heavy note.

The port encodes the legacy of McLean,
The truck man holding the rectangular dream.
The fifty-six voyage of the Ideal X
Replaced the sling and bale with standard steel.
The three-minute hook cycle built a world.
The break-bulk gangs dispersed into the past.
The brass checks vanished from the hiring hall.
The Mechanization and Modernization pact
Signed the longshoremen to their quiet pensions.
The diesel machines inherited the aprons.
The automated tracks assumed the labor.

The carbon cycle forms a perfect ring.
The ancient saurian died within the swamp.
The heavy earth compressed the bone to oil.
The refineries burned the oil to forge the steel.
The engineers shaped steel into the crane.
The crane assumes the brontosaurian stance.
The true self wakes inside the false self’s frame.
The massive beasts remember how to stand.

The port lies flooded under tidal glass.
The guard-house holds a pool of ocean rain.
The catenary wires catch the wind.
The gulls nest high upon the trolley tracks.
The silent giants watch the water rise.
They turn their glass-floored cabins to the sea.
They hold their patient posture in the mist.
The estuary swallows up the rail.
The cranes fulfill their long and final shift,
Wading the primeval marsh forever.

Kimi K2.5 Thinking was not bad, but didn’t contribute much in the end except some eccentric suggestions like a sestina:

Upon the bay the crane stands tall and white,
Lifting the box that holds the world’s desire,
While fog obscures the edges of the night.
The bone of saurians, compressed by fire,
Became the oil that drove the engines’ wheel,
And shaped the steel that made the port’s ordeal.

The longshoremen knew well the dockside ordeal,
Shaping up at dawn beneath the crane,
Their muscles harder than the tempered steel,
Their hands that moved the cargo, box by box,
Before the fossil fuel, the ancient fire
Of labor, met the cold Pacific fog.

Now McLean’s vision cuts through time and fog,
The Ideal X that ended one ordeal
And started another, breathing new fire
Into the self-moving beast, the crane
That needs no hands to lift the box
But runs on diesel, black and steel.

The A-frame giants, welded from the steel
That smelted in the carbon-swirling fog
Of prehistoric forests, lift the box,
The circle closing in this strange ordeal:
The dinosaur returns as towering crane
To lift its own remains, consuming fire.

They wade through mist like ghosts of ancient fire,
These brontosaurs of girder and of steel,
Their booms extended like the pleading crane
In grey mythology, through endless fog,
That wraps around the terminal’s ordeal
And hides the ships that bear the box.

What moves within? What animates the box?
The trace of true self, the compressed fire
Of life before the era of ordeal,
Before the rust, before the tempered steel,
Before the post-human fog,
Before the last remaining crane.

Envoi:
Steel crane and fog-bone, box of fire,
Oil of night, complete the ordeal.

And as usual, DeepSeek-v3 had some interesting ones but they were too heavy on meta-fictional elements, over-explaining, and “eyeball kicks” to try to mine or risk contaminating the others, so I dismissed them out of hand.

Surprisingly, Claude-4.6-opus performed very well, and produced most of the best candidates. I don’t entirely know why, since I usually regard Claude as relatively uncreative and mode-collapsed on a semantic level and its poetry is usually unsatisfying despite its often superior wordsmithing, but it may be that there was not enough creative room for Kimi or GPT to come up with anything brilliant, while Gemini was not even in the running.

Last but certainly not least, GPT-5.4 Pro served its usual role of careful balanced critique—although the 20–50-minute generation times made it a challenge to use.

Hybridization

I ran through several iterations before “hybridizing” (usually expanding the prompt and starting a fresh session, as a kind of poor-man’s “context distillation”), and then bringing in my more advanced ‘scaffolding’ requirements:

…I have used LLMs to brainstorm a large set of draft poems to recombine and modify into a final poem. We need to take the candidate hybrids and start carefully critiquing and revising them.

Procedure

As part of the revision, you will need to write out poems in an augmented form, with each line written normally and then in a scansion-notated form in HTML comments. The exact form of scansion is copied below.

To write this hybrid poem, brainstorm poem candidates based on this prompt and the samples. Write 5 hybrid poem candidates. To do so, for each candidate:

define the formal structure of the poem in lines, meter, rhyme scheme, length, etc.

write out a summary of the poem, first as an abstract, and then stanza by stanza

write out some sample lines from the hypothetical candidate. (Remember to include scansion.)

revise and critique the approach. After that,

write out the entire candidate poem. (Each line must have the scansion!)

revise and critique the candidate poem at least 3 times, starting with an analysis of how well it works globally, and down to the line by line level.

write out the final candidate poem.

analyze and evaluate; rate it 1–5 stars.

excerpt the best lines, images, phrases, and tricks from it.

Finally, write out a single hybrid poem with all of the best parts of all poems to create a single unified, complete, poem…

The scaffolding requires the LLM to write out a formal analysis of each line. This helps avoid regression while editing, and allows a laser-focus on the language. (I speculate that it also helps with tonal or register or formal shifts, because the LLM can write those down explicitly, and this gives the chatbot personality “permission” to write freely.)

I developed the inline metadata trick for writing “Your Hands and Mine”, where I noticed that GPT would keep slipping up and introduce a rhyme/syllable error after fixing another, as if it had blind spots or its working memory got overloaded. This made sense to me, because LLMs do not do well at highly reliably tracking a lot of implicit mutable state, like tracking syllable count and stress and rhyme per line across a whole poem, while also trying to actually think about the semantics and esthetics, so similar to arithmetic, we help the LLM by forcing it to write out notes to a scratchpad—and since it is Markdown, we can just stuff them into an easy HTML comment. (The metadata headers are also fascinating to read in showing how close a reader LLMs can be, and skilled at literary criticism and verbalizing things I would struggle to, while still struggling with phonetics; the impression one has is of a born-deaf professor of rhetoric analyzing a poem at the blackboard.)

For example, the first line in the Markdown source looks more like this:

<!-- SECTION A (L01–L10, OE + lacunae): job = invoke ruin and
manuscript-fragment together; domain = Exeter Book / industrial archaeology;
tone = awed, broken; structural-enjamb = drop to single-word L08 and
then damaged fragments; key-allusions = ‘The Ruin’, giant-work,
manuscript loss. -->

...

These crane-corpses, wondrous— / calamity crumpled them,
 <!-- L01 OE: 3+2: CRANE-CORPS-es WON-drous / ca-LAM-i-ty CRUM-pled. --> \

Visual Paratext

While I was waiting on this, I had Gemini brainstorm illustration ideas for Nano Banana Pro, like:

I am writing a poem about the Oakland port, the dinosaur-like cranes, in the fog etc. Attached is the current prompt/examples. I want you to brainstorm image illustration ideas for the poem’s thumbnail. The obvious one is some sort of brontosaurus-crane-hybrid in the fog. But come up with 20 more image prompt ideas; write them out, evaluate, critique, improve, and rate 1–5 stars.

I then generated the best 5, but I didn’t like them:

I’m not sure any of these are really working for me. They may be undone by their insistence on photorealism… comes off as HDR and Instagram slop-esque and not showing any insight. Let’s redo the brainstorming but this time go for more abstract, figurative, minimalist, or otherwise heavily stylized ideas.

This worked better when it yielded:

4. The Cyan/Black Woodcut (Concept 2)

Prompt: A harsh, high-contrast medieval woodcut block print of a ruined industrial crane. The image is composed entirely of jagged, rough black ink lines against a stark, flat cyan background. The heavy steel beams of the crane are carved to look like an exposed skeletal ribcage. Deep, physical gouge marks in the wood block swirl around the crane to simulate thick fog. Analog texture, visible carve lines, ink relief print style, brutalist and archaic. No photorealism, purely 2D graphic art.

Curation & Authorship

Once I had a final hybrid poem from each LLM, I had Claude choose the best one to work with, because it seemed like all the LLMs consistently ranked its poems highest on average.

Only at this point did I begin reading the poem in earnest and making manual edits. Primarily, adding reference hyperlinks and adding metadata commentary, although I also had to decide a few factual questions: the LLMs were troubled by the potential overclaiming of the Oakland playground, and I decided the esthetic effect was too important and if anyone was misled, that was permitted by poetic license.

After a first manual pass to acquaint myself with it, I then ran the Poetry magazine prompt to refine it.

This yielded only a handful of edits before I declared it done. (The biggest edit was killing a line explicitly stating the dinosaur/oil meme.) I then checked it all against the Manual of Style, as usual finding many errors. Then I wrote this Colophon.

AI Interview

Finally, with the poem finished, I used my “interview prompt” to generate interesting questions to answer; examples:

GPT-5.4 Pro:

Where do you think authorship lives here?

Why publish such a process-heavy colophon on the poem page instead of exiling more of it to graveyard notes?

Which factual compression were you most willing to tolerate, and where was the red line?

Why bless the cranes to stay rather than dismantle them or let them vanish?

Does the ending imagine immortality, extinction, or translation?

What threshold of manual revision makes an LLM poem decisively “yours”?

How much labor politics did you intentionally suppress?

What does “Vessel.” finally mean to you?

What line did you most distrust but keep?

If you reopened the poem, what single change would most improve it?

Claude-4.6-opus:

The colophon says you did “even less wordsmithing than usual” and made no “crucial” curation decisions. At what point does the author become primarily a prompt engineer / process designer rather than a poet? Do you have a principled threshold, or is it purely vibes?

You flag several lines as sounding “chatbot-ish”—the chiasmus about children/cranes/dinosaurs, the “theorems in a language no one speaks”, the “loneliest address a structure knows.” What is the specific quality that makes a line sound like a chatbot, and why couldn’t you fix it?

You mention wanting to “force more experimentation in meter—perhaps lean much more into the damaged fragments idea, or try to invent an entirely new meter to reflect a strange posthuman future.” Why didn’t you? What’s the actual bottleneck—LLM capability, your own time/attention, or something about the workflow that resists radical formal invention?

The “dead bone to oil, oil into fire, fire to steel, / and steel to the shape of bone again” chain is the poem’s thesis, but the commentary pre-emptively concedes it’s “symbolic genealogy, not petroleum chemistry.” How much does factual accuracy matter in a poem that’s partly about the power of mythic compression?

“Silver Bird” and “Craneyard” are both Bay Area elegies for obsolescent infrastructure, both involve posthuman speakers, both use a refrain with semantic drift. What’s the overall project here—is there a planned sequence, and what would the third one be?

Gemini-3.1-pro-preview:

If “authorship” remains yours because the high concept constrained the LLM, at what level of abstraction does a high concept become a mere prompt?

You mention a planned third poem about OpenAI’s Stargate facility. How will its formal structure differ from the aerospace and crane elegies?

Why do you think the LLMs consistently ranked Claude-4.6’s poems highest?

Does forcing the LLM to output explicit HTML scansion comments (cognitive load) degrade its semantic creativity?

Section D uses cold, bureaucratic documentary text (“ASSIGNED AREA: Outer Harbor.”). How well do current LLMs handle sudden, violent tonal shifts within a single generation pass?

Kimi K2.5 Thinking:

Why keep ‘chatbot-ish’ lines if they sound like LLM defaults?

Does scansion metadata reveal something about how LLMs ‘think’?

Is there political argument about automation, or pure image?

What would the datacenter/Stargate poem’s formal structure be?

Is the Velveteen Rabbit reference too sentimental?

[I don’t think it is, as it is so subtle that I’m sure every reader will miss it. It is more of a personal touch for me, given my interests in uploading; see also “Apollonian #2”.]

Then I published it.

Assessment & Open Questions

Overall, this took about a day of work, most of it spent waiting on long LLM runs and copy-pasting back and forth with little editorial or creative input on my end after the initial setup.

Authorship-wise, I list myself as the primary author, despite doing even less wordsmithing than usual and not making any ‘crucial’ decisions in terms of curation or selection (similar to the major decisions I made in creating “Tilakkhana” out of several unrelated samples). If you read through the early samples in the graveyard file, there’s less variety than in past experiments like the “This Last Pain” graveyard; and when they are drastically different, they tend to be weak and flabby, especially the more transhumanist sci-fi-heavy takes. Nothing here wound up truly surprising me—there was no idea which, upon search, escaped its creator and surprised them with unexpected depth. So in this case, I had an unusually specific, detailed high concept as a starting point, which constrained the LLMs too much to rise to the level where I would list Claude as the first author. And this may explain why Claude could shine here.

Had I intervened more, I think I would have tried to force more experimentation in meter—perhaps lean much more into the damaged fragments idea, or try to invent an entirely new meter to reflect a strange posthuman future somehow (similar to the invented alliterative meter in “Apollonian #1” which tries to reinvent Pindar); and considered the politics of Oakland more, as the deep research reports turned up interesting American politics I was unfamiliar with, and as it is, there is not much commentary there beyond a vague technological inevitability.

But I didn’t feel I had the time or energy to do so, as Inkhaven 2 was running, and I am backlogged on several poetry projects as it is (the “coastal spondaic” invented meter, or properly writing up the “pressure-cooker” meter of “Apollonian #1”). Perhaps I also lacked faith in the LLMs being able to find an ‘interesting’ meter which could reflect all of the influences simultaneously, and settled for a more straightforward historical progression of meters?

And a few parts wound up making me uneasy with how much they sound like chatbots: “The children played at cranes. The cranes played back / at dinosaurs. The joke outlived the crowd.”, or “like theorems in a language no one speaks.”, or “Between the ruin and the monument: / the loneliest address a structure knows.” They are too pat and aphoristic, too tidy, too regular and metronome-like; I would have improved them, or at least considered them at greater length, if I had more time and wanted to intervene more in this demonstration.

I was also not particularly sold on the triptych of “Vessel”, which doesn’t function as elegantly as “so much depends” does in “Silver Bird”; the repetition is OK but it lacks insight.

But overall, I am satisfied with the result and with how little manual effort I had to put into it with my refined workflow, and I hope the simplicity of my prompts will inspire people to be more ambitious with their own LLM usage (and not settle for the kind of AI slop they usually do).

Demand more of your LLMs, and give them the data and time that they need to really think!

Error: JavaScript disabled.

Backlinks, similar links, and the bibliography require JS enabled to load.

Bibliography

[Bibliography of links/references used in page]

A Strict Pindaric Meter

Gwern Branwen — Wed, 01 Apr 2026 00:00:00 GMT

GPT-5 proposed a new English “strict-triadic” Pindaric meter: accentual 8b/7b/8b strophe and antistrophe, followed by a shorter 6b/6f epode. The point is not classical reconstruction but audibility: an English line-shape that preserves the turn / counter-turn / stand of a Pindaric ode.

I tested the form against Richard Lattimore’s translation of Pindar’s “Olympia 2”. I did this using the “test translation” prompting strategy of repeatedly having the LLM specify a possible meter, ‘translate’ an existing high-quality poem into it, evaluate the result to critique the meter, and refine the meter.

The result shows real strengths—especially in gnomic and civic passages—but also predictable failure modes: stress-saturation, padding, and awkward handling of names and catalogues.

What follows is the working meter definition, a full test translation, and a side-by-side comparison with Lattimore.

The experiment does not solve the English Pindaric problem, but it yields a viable constraint worth further revision.

In September 2025, I was intrigued by GPT-5’s attempt at rendering my poem concept as a Pindaric ode, which is difficult because there is no generally agreed upon English verse form which could be considered equivalent (“Pindarics” notwithsntanding). The draft was unsuccessful but interested me enough to revisit it periodically, including having GPT-5 invent an alliterative Pindaric ode format (dubbed “pressure-cooker”) to write Apollonian #2, which was highly successful.

Sometime after, the ChatGPT “Pulse” feature suggested a new “strict” Pindaric ode format:

Here are two clean, practical ways to frame a modern Pindaric ode without losing the triadic “turn / counter-turn / stand” feel—one strict and audible, one freer but rhetorically locked.

Strict-triadic (accentual template)

Goal: keep the audible triad by mapping Greek cola → English stress-units so strophe & antistrophe are metrically identical and the epode “snaps” shorter.

Strophe / Antistrophe: 3 cola-lines each, stress counts [8, 7, 8], with a medial caesura after stress 4.

Epode: 2 shorter lines [6, 6] with final catalexis (dactylic “drop” feel).

Sound: alliteration > rhyme; enjamb with restraint between cola; keep lineation visibly parallel across the S/A.

Scansion key (pasteable as HTML comments):
S1 L1: i8: 8: the1 BEST2 is3 WA4-ter5; // caesura after stress4
S1 L2: i7: 7: NEXT2 GOLD3 that4 FLAMES5 by6 NIGHT7
S1 L3: i8: 8: GODS1 GRANT2 BRIGHT3 GIFTS4; MEN5 PRAISE6 the7 GIVER8
A1 L1: i8: 8: the1 BEST2 is3 WA4-ter5; // mirror S1 L1
A1 L2: i7: 7: NEXT2 GOLD3 that4 FLARES5 at6 NOON7
A1 L3: i8: 8: SONGS1 SPEND2 their3 BREATH4; CROWNS5 CLAIM6 the7 CLIMB8
E1 L1: i6: 6: SHORT1 LINE2 SNAP3 toward4 REST5
E1 L2: i6: 6: THEN1 FALL2 (un)SAID3 to4 GROUND5
Authoring checklist (1):

Write the strophe first; clone its stress map to the antistrophe.

Mark the mid-line || break after stress 4 for the long lines.

Let the epode’s last foot truncate (visual + acoustic release).

I liked the idea as a variant of the pressure-cooker, and had GPT-5 test it with Richard Lattimore’s translation of Pindar’s “Olympia 2” (from The Odes of Pindar, 1971), using my ‘test translation’ workflow.

Test Translation

The pressure-cooker meter’s development relied on a ‘test translation’ approach: have the LLM write out a semi-formal specification of a meter, then rewrite or ‘translate’ an existing poem (“Olympia 1”) into it, and evaluate where it struggled and how to fix the specification.¹

Concept → Formal Specification → Test Translation → Failure Analysis → Constraint Revision → Original Composition → Evaluation

Comparison of normal poetry writing to LLM-centric ‘test translation’.
Traditional Poetic Development	Test Translation Method
Poet develops ear for form through reading and imitation	LLM formalizes explicit constraint set
Rules remain tacit, embodied	Rules become explicit, auditable
Revision based on aesthetic intuition	Revision based on systematic failure modes
Single-author evolution	Collaborative human/LLM debugging

The document shows this process working in real-time:

Initial specification (GPT-5’s “Pulse” suggestion): 8b/7b/8b + 6b/6f
Stress-test (“Olympia 2” translation): Identifies “fake ictus”, “short-line inversion”, “stress-saturation”
Refinement: “Syllable corridors”, caesura flexibility rules, prohibition on artificial stress

After several iterations, GPT-5 was satisfied, and produced a final definition and test translation (comparison), below.

Strophe I [Anchor A], named first, for reasons you can drink. [Anchor B], named second, because flame measures distance at night. [Anchor C], the human counter, spent where breath and laurel meet. Antistrophe I [Anchor A] returns, but under pressure—refracted. [Anchor B] returns, but alloyed—spent for light. [Anchor C] returns, but broken—voice against the brass. Epode I Therefore: gather them once, weigh them twice, and set them down.

Strophe I My SONGS, lords OF the LYRE, aWAKE || and SPEAK TRUE, STRAIGHT—NOW. WHAT GOD, what HE-ro, what MAN shall WE || NAME, and PLACE in SONG? ZEUS HOLDS the PI-san FIELD; || HERakles RAISED its FAME from SPOILS. Antistrophe I He SWEPT the WAR's reMAINS, and SET || the RACE: START, TURN, GOAL. but THEron's FOUR-horse WIN we MUST || SING; he CLAIMS our VOICE. KIND to the GUEST, THEron STANDS || AKRagas' TOW-er, FLOWER of his LINE. Epode I So DRAW the STRING, and LET our PRAISE fall TRUE. THEron, bear HOME this SONG; it SHALL LAST.

-----

STROPHE I My songs, lords of the lyre, awake || and speak true, straight—now. what god, what hero, what man shall we || name, and place in song? Zeus holds the Pisan field; || Herakles raised its fame from spoils. ANTISTROPHE I He swept the war’s remains, and set || the race: start, turn, goal. but Theron’s four-horse win we must || sing; he claims our voice. Kind to the guest, Theron stands || Akragas’ tower, city’s guard. EPODE I So draw the string, and let our praise fall true. Theron, bear home this song; it shall last long. STROPHE II Through hard toil of the mind, they shone, || Sicily’s watchful living eye. By river they kept the sacred house || and held the threshold clean. Their doom came on; their valor held || wealth; and delight came down, came near. ANTISTROPHE II But Kronios, Rhea’s son, who guards || Olympos’ throne, steadfast, high, and still, and Alpheus’ ford, and games’ renown, || in gentle mood, give aid. For song’s own sake, keep them and theirs || the fatherland, through rest of seed. EPODE II No just, no crooked deed can Time undo—ever. But forgetfulness can come; bliss hides pain still. STROPHE III Grief, roused again from quiet, || at last lies dead beneath good things. when God-sent Fortune drops its gold || deep from above, and fills. So Kadmos’ queenly daughters proved || long pain will yield to growing gain. ANTISTROPHE III Semele, soft-haired, struck by thunder, || lives on Olympos, dear to Zeus. and Pallas loves her still; her son || with ivy staff rejoices. They say, in sea-deep Nereids’ hall, || Ino is given life unbroke. EPODE III For mortals, death sets no known term here. Day runs; delight and labor pour streams down. STROPHE IV No man can mark the death-day; || nor end the sun’s child, day, in pure. Stream upon stream of delight falls || with labor blended in. So Fate, her Father’s guiding hand, || sends wealth from God, and sends us pain. ANTISTROPHE IV So Laios’ doomed son met him, || and killed, and made the oracle true. long spoken once at Pytho’s shrine; || Erinys saw, and hated. and slew his mighty race by hands || of kin; yet one green shoot remained. EPODE IV When Polyneikes fell, Thersandros stood for honor still. A branch to shield old Adrastos’ house again, still. STROPHE V From that same stock, Ainesidamos’ son, || is fit for song and lyre and praise. He took Olympia’s crown himself; || and Graces set more flowers. His brother, equal in right also, || at Pytho, Isthmos, won it too. ANTISTROPHE V Such success washes sweat away; || the striver’s toil turns light in hand. Wealth, wrought with virtue, opens doors || for diverse work and deed. it bears the cruel depth of care, || star-bright, the truest shine of man. EPODE V If one keep wealth, and know what’s coming well. Down there, a judge weighs sin, gives doom. STROPHE VI When we die here, the heart unruled || pays back its debt; no loose deed sleeps. for wrong in God’s own kingdom, there || is trial under earth. in dark constraint of wrath, he sets || the sentence; still the scale stands hard. ANTISTROPHE VI But nights equal forevermore, || and days with equal sun, befall the good. They live without hard labor; they || move no earth, no sea, for bread. Beside the high gods, those who kept || their oath find joy; and tears return no more. EPODE VI The rest look on that blank-faced evil, unblinking, still. Thrice-tried, they find God’s road to Kronos’ keep. STROPHE VII There Ocean winds blow cold and sweet, || across the isle where blessed men abide. Gold flowers flare on land, on trees; || and gold is fed by wave. From water there they weave bright wreaths, || and bind their arms with bracelets shining round. ANTISTROPHE VII Under straight laws of Rhadamanthys, || they walk, all chapleted, in measured joy, calm. whom Rhea’s spouse, high throned, keeps close || beside him, great in state. They say Peleus is there, and Kadmos, || and Thetis, prayer-soft, bore Achilles home to them. EPODE VII He felled tall Hektor, Troy’s firm pillar, down. and slew Kyknos, and Memnon, Dawn’s son, too. STROPHE VIII I hold, beneath my arm’s bent crook, || full quivers—many sharp shots for thought. They speak to minds that understand; || the many need guides along. The wise man knows much within blood; || the base are taught, and chatter what they hear, loud. ANTISTROPHE VIII They say what ever serves; they clack || like crows against Zeus’ eagle-wing. No wisdom there; the fool is drilled || and still thinks himself wise. So come, my heart, now bend the bow, || and loose kind arrows: mercy, not malice. EPODE VIII Toward Akragas we aim, and speak our oath, true, now. A straight word from the mind, without a lie, here. STROPHE IX Not in a hundred years has city born || a kinder friend, a hand more open-wide. than Theron. Yet envy rides on praise, || not yoked with justice, still. The sneerers’ slander would conceal || fair deeds of noble men; but secrecy fails. ANTISTROPHE IX For sands escape all number; so, || of joy that Theron gave, who counts the sum? What tongue could tell the measure out, || or set its end in words? I loose these shots, not all, but true; || the rest is sea, unsounded, left for God. EPODE IX So let this song stand firm: Theron, friend. and let no envy cut the laurel down, here.

-->

Evaluation

The poem strikes me as somewhat clunky due to the required stresses and padding/compression (eg. “Guest-loving, Akragas’ tower, he stands || choice bud of a high line.”), but has a lot of merit, and some great lines from pushing the LLM out of its comfort zone (contrast the weak lines in “Human Perception at a Red Light”), eg:

“She cut the mighty race down, hand by hand, || in kindred blood and wrath.”
“Gold flowers burn on land, in trees; || the water feeds them too.”
“They say whatever comes; they clack like crows || against Zeus’ sacred bird.”
“Success can wash the striver’s striving clean || of strain and dust and ache.”
“Grief, breaking out from quiet, dies at last || beneath fair fortune’s weight.”
“What’s done, just or unjust, no Time the father || can ever leave undone.”
“The others face blank evil, featureless, mute.”

(Notably better than the original: “The rest look on a blank face of evil.”)
“They live without hard labor, troubling neither || earth nor sea for need.”

Strict Pindaric Meter

Definition for use in prompts:

STRICT TRIADIC v2
English accentual triadic meter

PURPOSE
Strict English triadic form meant to preserve the audible turn / counterturn / stand
of Pindaric ode, while avoiding the main failures exposed by the Olympia 2 test:
fake ictus, short-line inversion, stress-saturation, and over-closing epodes.

BASIC UNIT
One triad = Strophe + Antistrophe + Epode.

LINE COUNTS
Strophe:    8b / 7b / 8b
Antistrophe: 8b / 7b / 8b
Epode:      6b / 6f

Notation:
- b = beat / ictus
- f = feminine ending: 1 final unstressed syllable after the last beat
- 4|4, 3|4, etc. = principal caesura position

CORRESPONDENCE RULE
- Strophe and antistrophe must correspond line-for-line in beat-count and order.
- Beat-count is strict.
- Syllable count is corridor-based, not exact.
- Matching caesural shape is preferred on the 8-beat lines.
- On the 7-beat line, caesura may float with syntax.
- Triad boundaries are metrical, not necessarily sentence boundaries.

SYLLABLE CORRIDORS
8b line: 11–15 syllables
7b line: 10–13 syllables
6b line: 8–11 syllables
6f line: 9–12 syllables

ANACRUSIS
- 0–2 initial unstressed syllables are allowed before the first beat of any line.

CAESURA RULES
8-beat line
- Default shape: 4|4
- One 3|5 or 5|3 variant is allowed per triad if syntax strongly demands it

7-beat line
- No fixed caesura
- Place the principal break at the strongest syntactic joint nearest beat 3 or 4
- 3|4 and 4|3 are both normal

6-beat line
- No fixed caesura
- A hinge near beat 3 is common, but optional

ICTUS RULES
- Beats fall only on natural lexical stress
- Articles, auxiliaries, prepositions, conjunctions, and unstressed pronouns do not bear ictus
  unless they are contrastively stressed in ordinary speech
- Proper names scan by ordinary English pronunciation
- Do not promote or suppress stress artificially to solve the line

SLACK RULES
- In 8b and 7b lines, each side of the principal caesura must contain at least one unstressed syllable
- In 6b and 6f lines, the line as a whole must contain at least two unstressed syllables
- No run of more than 3 consecutive ictuses is allowed
- Unstressed syllables may expand freely between beats, so long as the line stays inside its corridor

ENDING RULES
- One feminine ending is permitted in any line
- The second epode line is normally feminine: 6f

EPODIC RULE
- The epode should hinge or release, not necessarily conclude
- The 6f line may run syntactically into the next triad
- The epode is therefore lighter than a couplet “verdict”

NON-RULES
- Rhyme is optional and not part of the meter
- Alliteration, assonance, and syntactic parallelism are encouraged but not required
- Exact syllable-matching between strophe and antistrophe is not required

COMPOSITIONAL WARNING
- Proper names and catalogue passages are the main pressure point
- When names or lists accumulate, add syllabic slack rather than forcing extra ictus

SCANSION KEY
- Mark beats, not syllables
- Mark the principal caesura only
- Example notation:
    8b 4|4
    7b 3|4
    6f

MINIMAL TEMPLATE
Strophe:
  L1  8b
  L2  7b
  L3  8b

Antistrophe:
  L1  8b
  L2  7b
  L3  8b

Epode:
  L1  6b
  L2  6f

Example Translation

[LLM “scaffolding” poetry metadata per the MoS]





Olympia 2

Strophe 1

My songs, lords of the lyre, awake || answer, and speak true now.
Which god, which hero, which man || shall the hymn name and set in song? [2 syllables over? —Editor]
Zeus holds Pisa; Herakles || from war-spoil built these sacred games.

Antistrophe 1

From battle spoil he founded, he ordained || race, altar, judges, crown. [1 syllable over? —Editor]
But Theron, chariot-four victor, || claims song; to him we turn.
Guest-loving, Akragas’ tower, he stands || choice bud of a high line.

Epode 1

Taut string, speak now and name him clear.
Theron, whose house still flowers from old ancestral stock.

In hard soul-labor they stood out || Sicilia’s watchful seeing eye.
Beside the river, they kept the sacred house || and held the threshold clean.
And fate drew on; by valor in their blood || wealth with delight came near.

Rhea’s son, Kronios, who guards || Olympos, games, Alpheus’ ford,
for song’s sake keep, in gentleness, their land || and all their future line.
What’s done, just or unjust, no Time the father || can ever leave undone.

Yet still good fortune sometimes brings forgetfulness.
and grief, once quiet, can rise, then sink beneath abundance.

Grief, breaking out from quiet, dies at last || beneath fair fortune’s weight.
When God’s decree lets wealth fall deep from heaven || and makes the burden sink.
So speaks the story of Kadmos’ daughters: || as goods wax, grief grows numb.

Semele, soft-haired, thunder-struck, lives still || on Olympos, loved of Zeus.
By Pallas loved, and dearest to her son || who bears the ivy bough.
They say Ino, deep with Nereus’ daughters, gains || deathless life.

No mortal knows the fixed term set by death,
when sun-child day may close in whole unbroken quiet.

Stream after stream of pleasures mixed with toil || comes down on mortal men.
So Fate, father-guided to this line, || still bestows pain in turn.
With wealth from God as well; later the blow || comes home to us again.

Thus Laios’ destined son, once met, slew him || fulfilling old Pytho.
The word long foretold there; and Erinys || looked on, and hated him.
She cut the mighty race down, hand by hand, || in kindred blood and wrath.

After Polyneikes fell, Thersandros stood for honor.
a living branch to shield Adrastos’ house again.

From that same stock, Ainesidamos’ son || may win lyre, praise, and hymn.
He took Olympia’s prize himself; || the garlanded strain is due.
His brother, equal-born, the Graces crowned || at Pytho, Isthmos, twelve-lap race.

Success can wash the striver’s striving clean || of strain and dust and ache.
Wealth wrought with virtue opens many doors || to manifold deeds.
It shoulders care’s deep cruelty, and shines || star-bright, man’s truest light.

Keep wealth, and know the coming judgment well.
For under earth a judge still waits, severe.

Here, dying, the heart without curb || pays back old debts in vengeance.
And for offences in God’s realm below || a judge sits under earth.
He gives sentence under wrath’s constraint || hard, final, without pleading.

But nights forever equal, days alike || beneath one equal sun.
They live without hard labor, troubling neither || earth nor sea for need.
Beside the high gods, faithful souls rejoice || and live a tearless life.

The others face blank evil, featureless, mute.
But thrice-enduring souls, from sin kept clear, go Kronos-ward. [7 beats?]

There by Kronos’ tower Ocean winds || blow across the Blessed Isle.
Gold flowers burn on land, in trees; || the water feeds them too.
From these they bind bright bracelets on their arms || and go garlanded, heads high.

Under Rhadamanthys’ straight decrees || they walk beside the chair of state.
Whom Rhea’s husband, throned above them all, || keeps near, great father.
There Peleus is, they say, and Kadmos too; || Achilles brought by softening prayer.

He felled great Hektor, Troy’s unshaken prop,
and killed Kyknos, and Memnon, child of Dawn, too.

Many keen shafts beneath my crooked arm || crowd close in quiver.
They speak to understanding; most men still || need interpreters.
The wise know much by nature in the blood; || the coarse learn from teachers.

They say whatever comes; they clack like crows || against Zeus’ sacred bird.
No inward measure guides them; drilled, they pose || as masters over all.
Come then, my heart, draw to the mark; bend || the bow with gentler purpose.

Whom shall mild, merciful shafts now strike gently?
Toward Akragas we bend, and swear a straight word.

No city in a hundred years gave forth || a freer, friendlier hand.
No man more kind to friends, more open-handed, || has stood than Theron here.
Yet envy rides on praise, though not with justice; || slander dogs noble deeds.

Reviling scandal would draw curtains round || fair deeds of noble men.
But sand escapes all numbering; who can count || what Theron gave?
What mortal tongue could take the full measure || of joy to others given?

Then let straight song answer back to envy.
For where he gave delight, no measure holds.

Comparison

Richard Lattimore’s free-verse translation set beside a strict-triadic recasting. Alignment is rhetorical rather than line-for-line philological: some source fragments recur where the recasting splits or anticipates them, and em dashes mark explicit metrical closures with no direct free-verse equivalent.

Lattimore (free verse)	Strict Triadic v2
Strophe 1
My songs, lords of the lyre,	My songs, lords of the lyre, awake \|\| answer, and speak true now.
which of the gods, what hero, what mortal shall we celebrate?	Which god, which hero, which man \|\| shall the hymn name and set in song?
Zeus has Pisa; but Herakles founded the Olympiad out of spoils of his warfare;	Zeus holds Pisa; Herakles \|\| from war-spoil built these sacred games.
Antistrophe 1
out of spoils of his warfare;	From battle spoil he founded, he ordained \|\| race, altar, judges, crown.
but Theron, for his victory with chariot-four, is the man we must sing now,	But Theron, chariot-four victor, \|\| claims song; to him we turn.
him of the kind regard to strangers, the tower Akragantine, choice bud of a high line guarding the city.	Guest-loving, Akragas' tower, he stands \|\| choice bud of a high line.
Epode 1
—	Taut string, speak now and name him clear.
—	Theron, whose house still flowers from old ancestral stock.
Strophe 2
In strong toil of the spirit they were the eye of Sicily,	In hard soul-labor they stood out \|\| Sicilia's watchful seeing eye.
they beside the river kept the sacred house;	Beside the river, they kept the sacred house \|\| and held the threshold clean.
their doom drew on, bringing wealth and delight near by the valor in their blood.	And fate drew on; by valor in their blood \|\| wealth with delight came near.
Antistrophe 2
But, O Kronios, Rhea's son, guarding Olympos' throne and the games' glory and the Alpheus crossing,	Rhea's son, Kronios, who guards \|\| Olympos, games, Alpheus' ford,
in mild mood for the song's sake kind keep for them always the land of their fathers the rest of their generation.	for song's sake keep, in gentleness, their land \|\| and all their future line.
Of things come to pass in justice or unjust, not Time the father of all can make the end unaccomplished.	What's done, just or unjust, no Time the father \|\| can ever leave undone.
Epode 2
But forgetfulness may come still with happiness.	Yet still good fortune sometimes brings forgetfulness.
Grief, breaking again out of quiet, dies at last...	and grief, once quiet, can rise, then sink beneath abundance.
Strophe 3
Grief, breaking again out of quiet, dies at last, quenched under the waxing weight of fair things,	Grief, breaking out from quiet, dies at last \|\| beneath fair fortune's weight.
with God's destiny dropping wealth deep from above.	When God's decree lets wealth fall deep from heaven \|\| and makes the burden sink.
Thus the tale for the queenly daughters of Kadmos, who endured much; grief falls a dead weight as goods wax in strength.	So speaks the story of Kadmos' daughters: \|\| as goods wax, grief grows numb.
Antistrophe 3
Semele of the delicate hair, who died in the thunderstroke, lives on Olympos, beloved of Pallas forever, of Zeus,	Semele, soft-haired, thunder-struck, lives still \|\| on Olympos, loved of Zeus.
best loved of her son with ivy in his hands.	By Pallas loved, and dearest to her son \|\| who bears the ivy bough.
And they say that in the sea among the daughters of Nereus in the depth, Ino is given life imperishable for all time.	They say Ino, deep with Nereus' daughters, gains \|\| deathless life.
Epode 3
But for mortal men no limit in death has been set apart	No mortal knows the fixed term set by death,
when we shall bring to an end in unbroken good the sun's child, our day of quiet;	when sun-child day may close in whole unbroken quiet.
Strophe 4
stream upon stream of delights mixed with labor descends upon men.	Stream after stream of pleasures mixed with toil \|\| comes down on mortal men.
Thus Destiny, who has from her father the kindly guidance of these men,	So Fate, father-guided to this line, \|\| still bestows pain in turn.
yet with wealth sent from God bestows some pain also, to return upon us hereafter.	With wealth from God as well; later the blow \|\| comes home to us again.
Antistrophe 4
So his doomed son killed Laios when they met, and brought to accomplishment	Thus Laios' destined son, once met, slew him \|\| fulfilling old Pytho.
the thing foretold long since at Pytho.	The word long foretold there; and Erinys \|\| looked on, and hated him.
And Erinys looked on him in bitterness and slew all his strong race at each others' hands.	She cut the mighty race down, hand by hand, \|\| in kindred blood and wrath.
Epode 4
Yet when Polyneikes fell, Thersandros remained for honor in the trial of fresh battles,	After Polyneikes fell, Thersandros stood for honor.
a branch to shield the house of Adrastos.	a living branch to shield Adrastos' house again.
Strophe 5
Stemmed in his stock, it is fit for Ainesidamos' son to win songs in his honor and the lyre's sound.	From that same stock, Ainesidamos' son \|\| may win lyre, praise, and hymn.
He himself took the prize at Olympia;	He took Olympia's prize himself; \|\| the garlanded strain is due.
to his brother equal in right the impartial Graces brought blossoms of honor for the twelve-lap chariot race at Pytho, at the Isthmos;	His brother, equal-born, the Graces crowned \|\| at Pytho, Isthmos, twelve-lap race.
Antistrophe 5
success for the striver washes away the effort of striving.	Success can wash the striver's striving clean \|\| of strain and dust and ache.
Wealth elaborate with virtue brings opportunity for various deeds;	Wealth wrought with virtue opens many doors \|\| to manifold deeds.
it shoulders the cruel depth of care, star-bright, man's truest radiance;	It shoulders care's deep cruelty, and shines \|\| star-bright, man's truest light.
Epode 5
if a man keep it and know the future,	Keep wealth, and know the coming judgment well.
there is a judge under the earth.	For under earth a judge still waits, severe.
Strophe 6
how, as we die here, the heart uncontrolled yields retribution;	Here, dying, the heart without curb \|\| pays back old debts in vengeance.
likewise for sins in this kingdom of God there is a judge under the earth.	And for offences in God's realm below \|\| a judge sits under earth.
He gives sentence in constraint of wrath.	He gives sentence under wrath's constraint \|\| hard, final, without pleading.
Antistrophe 6
But with nights equal forever, with sun equal in their days, the good men have life without labor,	But nights forever equal, days alike \|\| beneath one equal sun.
disquieting not the earth in strength of hand, never the sea's water for emptiness of living.	They live without hard labor, troubling neither \|\| earth nor sea for need.
Beside the high gods they who had joy in keeping faith lead a life without tears.	Beside the high gods, faithful souls rejoice \|\| and live a tearless life.
Epode 6
The rest look on a blank face of evil.	The others face blank evil, featureless, mute.
But they who endure thrice over in the world beyond to keep their souls from all sin have gone God's way to the tower of Kronos;	But thrice-enduring souls, from sin kept clear, go Kronos-ward.
Strophe 7
there winds sweep from the Ocean across the Island of the Blessed.	There by Kronos' tower Ocean winds \|\| blow across the Blessed Isle.
Gold flowers to flame on land in the glory of trees; it is fed in the water,	Gold flowers burn on land, in trees; \|\| the water feeds them too.
whence they bind bracelets to their arms and go chapleted	From these they bind bright bracelets on their arms \|\| and go garlanded, heads high.
Antistrophe 7
under the straight decrees of Rhadamanthys,	Under Rhadamanthys' straight decrees \|\| they walk beside the chair of state.
whom the husband of Rhea, high throned above all, our great father, keeps in the chair of state beside him.	Whom Rhea's husband, throned above them all, \|\| keeps near, great father.
They say Peleus is there, and Kadmos, and his mother with prayer softening Zeus' heart carried Achilles thither,	There Peleus is, they say, and Kadmos too; \|\| Achilles brought by softening prayer.
Epode 7
who felled Hektor, Troy's unassailable tall column of strength,	He felled great Hektor, Troy's unshaken prop,
who gave death to Kyknos and the Aithiop, Dawn's child.	and killed Kyknos, and Memnon, child of Dawn, too.
Strophe 8
There are many sharp shafts in the quiver under the crook of my arm.	Many keen shafts beneath my crooked arm \|\| crowd close in quiver.
They speak to the understanding; most men need interpreters.	They speak to understanding; most men still \|\| need interpreters.
The wise man knows many things in his blood; the vulgar are taught.	The wise know much by nature in the blood; \|\| the coarse learn from teachers.
Antistrophe 8
They will say anything. They clatter vainly like crows against the sacred bird of Zeus.	They say whatever comes; they clack like crows \|\| against Zeus' sacred bird.
The vulgar are taught.	No inward measure guides them; drilled, they pose \|\| as masters over all.
Come, my heart, strain the bow to the mark now.	Come then, my heart, draw to the mark; bend \|\| the bow with gentler purpose.
Epode 8
Whom shall we strike in gentleness, slipping merciful arrows?	Whom shall mild, merciful shafts now strike gently?
Toward Akragas we will bend the bow and speak a word under oath in sincerity of mind.	Toward Akragas we bend, and swear a straight word.
Strophe 9
Not in a hundred years has a city given forth	No city in a hundred years gave forth \|\| a freer, friendlier hand.
a man kinder to his friends, more open of hand than Theron.	No man more kind to friends, more open-handed, \|\| has stood than Theron here.
But envy bestrides praise, though coupled not with justice; still the revilers' scandal would put secrecy upon fair deeds of noble men.	Yet envy rides on praise, though not with justice; \|\| slander dogs noble deeds.
Antistrophe 9
still the revilers' scandal would put secrecy upon fair deeds of noble men.	Reviling scandal would draw curtains round \|\| fair deeds of noble men.
For sands escape number,	But sand escapes all numbering; who can count \|\| what Theron gave?
and of all the joy Theron has brought to others what man could tell the measure?	What mortal tongue could take the full measure \|\| of joy to others given?
Epode 9
—	Then let straight song answer back to envy.
—	For where he gave delight, no measure holds.

This reminds me a little of using AlphaZero to investigate possible changes to the rules of chess, or reconstructing lost historical game rules.↩︎
In the famous description of Horace:

A river bursts its banks and rushes down a
Mountain with uncontrollable momentum,
Rain-saturated, churning, chanting thunder—
There you have Pindar’s style.

↩︎

Error: JavaScript disabled.

Backlinks, similar links, and the bibliography require JS enabled to load.

Bibliography

[Bibliography of links/references used in page]

Human Perception at a Red Light

Gwern Branwen — Tue, 24 Mar 2026 00:00:00 GMT

This essay tests a simple claim by an LLM: that a particular human poem had a real subject but weak realization.

On 2026-03-15, I asked GPT-5.4 Pro rewrite it under explicit formal constraints; it chose to invent a sonnet, a split-screen human/machine poem, and an alliterative version. I then iterated them using scansion and cross-model critique.

The rewrites are better. Constraint improves cadence, imagery, and closure, and the split-screen version in particular turns theme into form rather than merely paraphrasing it.

But the gains are mostly local: revision critiques execution, and does not expand the space of possibilities. Constraint raises the floor for LLM poetry. It does not raise the ceiling. What is necessary is to expand the room, and break the walls, by adding more, such as necessity. None of the rewrites become major poems, because formal optimization cannot supply what is missing: conceptual surplus, allusive depth, and pressure from material outside the poem’s initial premise.

I take this as further evidence that LLM poetry benefits from many runs, explicit concept-loading, and large models.

Every task involves constraint,
Solve the thing without complaint;
There are magic links and chains
Forged to loose our rigid brains.
Strictures, structures, though they bind,
Strangely liberate the mind.

—James E. Falen ¹

ChatGPT Pulse brought up a recent poem on the theme of AI: “Artificial neurons can be trained to kill humans without humans overseeing”, K. A. Hays (2026-01-29):

I read on my iPhone, stopped at a red light, & next to my car
a child is playing a street piano fast, counting THREE, TWO, ONE,
yelling over traffic, I’m PLAYING, sun on the child’s face

& fingers skittering on keys—
neurons direct these fingers, a consciousness no one shares
that says, high notes now, then low, & laughter,

& an adult urges the child to come-on-let’s-go, but the child plays a crescendo & says
I AM FINISHING MY SONG—

& artificial intelligence can use recurrent neural networks to create
piano music & AI can drive cars, but my eyes tire,
my eyes are animal eyes with animal need to gaze out

at red lights & be given the useless-lovely data of a sparrow skimming
to a telephone wire, a child at a rainbow-painted stringed instrument,
the sparrow hopping on a wire, the child pressing keys like a question:

low, high? Low, high? Perception a note not played again,
& when the light turns green my car drives,
I am finishing my song. The light is yellow now.

I didn’t care for it, and said as much, and GPT agreed:

…Yes—that’s exactly where it thins out.

The poem’s idea is doing nearly all the work; the language is mostly just transporting it. You can feel that in a few places:

The lineation is arbitrary. Breaks don’t create pressure (no enjambment tension, no rhythmic pivot), so as you noted, it survives flattening into prose with minimal loss.

The sonic field is underdeveloped. There’s little patterned recurrence—no real alliterative spine, vowel harmonics, or metrical expectation being set up and then varied. The diction is competent but not charged.

Syntax is default expository. Clauses proceed in a “thought, elaboration, contrast” pipeline that reads like an essay paragraph broken into lines.

The key problem isn’t that it’s free verse; it’s that it’s uncommitted verse. Compare to something like Jorie Graham or Carl Phillips, where even without strict meter, you still get:

controlled breath units (line = perceptual event),

recurrence structures (lexical, syntactic, sonic),

pressure from delay/suspension.

Here, the closing claim—“my eyes are animal eyes”—should land like a volta, but it isn’t prepared musically. It arrives as a conceptual assertion rather than a sonic inevitability.

How to strengthen it (without turning it into a sonnet):

Impose a constraint you can feel.

Even a loose accentual scheme (say, 3–4 stresses per line, with periodic deviations) would give the reader something to ride.

Exploit the image system sonically.

The sparrow/piano/fingers cluster is begging for patterned consonants (sk-, tr-, p-) and percussive echo to mirror the tapping.

Make the line breaks do work.

Break against syntax so that key words are delayed or doubled in meaning. Right now, most breaks are after-comma pauses.

Engineer the volta.

Seed “animal” earlier—phonically or imagistically—so the final line resolves a pattern rather than introducing a thesis.

Cut abstraction by ~20%.

Every abstract noun that remains should earn its place via placement or echo, not just semantic necessity.

Put bluntly: the poem knows what it wants to say, but it hasn’t decided how language must behave to make saying it unavoidable.

This was a bold set of claims, and I became curious if it could indeed fix the poem autonomously without degrading the way that “Spoilage” had (although I didn’t want to push the revisions as far as “Spoilage”).

So I told GPT-5.4 Pro to fix it with my usual brainstorm-style prompt (followed by requiring use of my usual poem commentary & scansion markup to help scaffold revision):

Try rewriting it. Brainstorm 10 detailed revisions aiming at different effects. Revise each one repeatedly. Rate them 1–5 stars and print out the final top 3…for the 3 finalists, apply the Gwern.net Scansion MoS format, and revise and iterate. Critique and analyze the resulting versions.

First Draft

The 3 top GPT-5.4 Pro responses:

Sonnet (first):

At red, the street lies still beneath a hush,
The lamps go soft and smear themselves to gold.
A boy taps wrong notes through the traffic rush,
Until those wrong notes answer bright and bold.

It marks the car that moves a breath ahead;
It holds the lane and warns my foot to wait.
It reads the painted curb, the stripe, the red;
But not the grackle riding out the weight.

My phone reports new systems choose and track;
A body’s heat through dust without a guide.
Above, the grackle writes the wind in black.
And shifts by grams no model can decide.

Let sensors spare me glass and closing door;
I live by what no tally can restore.
“Split-Screen” (first):

Lane-lock active; distance maintained.
In rain, a boy combs sparks from out the keys.

Pedestrian motion plotted.
One grackle flexes, black against the span.

Hazard model tuned overnight.
One sour note opens outward through the stop.

Target module cleared in field tests.
Cold pennies wake along the rails in rain.

Recommendation: apply brake.
I brake—for one bird leaning on the gust.

Recommendation: proceed now.
I go, and keep the weather, not the map.
Alliterative (first)

Brake-bloom, bus-hush || blackbird on cable,
Boy by bus-stop || beats bent keys,

Screen scans street-lines || spots steel danger,
Feed touts fire-tools || free of hands.

Toe-grip on pedal || tin-note, thaw-breath:
By blood they come || by blink, by bone.

Circuits can count || the crowd below;
No wire can weigh || weather home.

Revision

I then required:

Analyze and critique the 3 AI poems as a response to and improvement on the human poem.

Putting it into Kimi K2.5 Thinking, Claude-4.6-opus, & Gemini-3.1-pro-preview for critique, and then having GPT-5.4 Pro revise and update based on the feedback:

Please read carefully, agree/disagree with critiques, and revise all 3 iteratively to improve after brainstorming at least 10 possible improvements to each one in light of the valid or invalid comments from your fellow LLMs.

Second Draft

This yielded the final versions:

Sonnet (final):

At red, the street lies still beneath a hush,
The lamps go soft and smear themselves to gold.
A boy taps wrong notes through the traffic rush;
“I’m finishing my song”, he shouts in bold.

The screen brackets the car that moves ahead;
It holds the lane and warns my foot to wait.
It reads the painted curb, the stripe, the red;
But not the grackle riding out the weight.

My phone reports new systems choose and track;
A body’s heat through dust without a guide.
Above, the grackle writes the wind in black
And shifts by grams no model can decide.

The light goes green. “I’m finishing my song.”
I hold one yellow beat; one horn grows long.
Split-Screen (final):

Lane-lock active; interval held.
In rain, the boy combs sparks out of the keys.

Pedestrian vector plotted.
A grackle flexes black along the wire.

Hazard threshold tuned overnight.
He shouts, “I’m finishing my song”, through rain.

Target module cleared in field tests.
Cold pennies wake along the rails in rain.

Recommendation: apply brake.
I brake—for one bird leaning on the gust.

Recommendation: proceed now.
I go, and keep the weather, not the map.
Alliterative (final):

Brake-lights bloom || bus brakes sigh,
Boy at curb-piano || batters bright keys,
Shouts, “I’m finishing!” || back through rain.
Screen scans street-lines || stripe, curb, red.
Phone-feed flashes || field-test footage:
Body-heat boxed || body tagged threat.
Black grackle balances || bends to crosswind.
Brake-foot follows || that black leaning.
Tin rails ring || cold in the rain.
Circuits count bodies || crowding below.
No wire can weigh || weather home.

Evaluation

Then I asked GPT-5.4 Pro to compare them:

…Final comparative judgment:

After revision, the hierarchy changes a little. As responses to Hays:

split-screen > sonnet > alliterative.

As standalone poems:

sonnet ≈ split-screen > alliterative.

The sonnet is now far less bloodless than before. The split-screen is still the most intelligent formal answer to the source poem’s actual problem. The alliterative version no longer fights the material, but it works by becoming something narrower and harder than Hays—a compressed urban spell, not a complete rival.

The real lesson from the 3 external critiques is that the valid complaint was never “these poems are too formal”. The valid complaint was “they had gained form by losing interruption”. These revisions fix that.

Did the formal structure and revision help? Yes.

I think that the constraints and iteration/critique did improve the 3 poems; but that GPT-5.4 Pro is wrong in saying the sonnet is ever as good as the split-screen. I think the split-screen is clearly superior to both, although they have some good points (eg. “grackle” is more interesting than Hays’s “sparrow”). And I think overall, I’d still prefer to read the final split-screen to Hays’s original poem.

But none of them are great. I’d say “good, but not memorable”; I could probably come up with something better than it if I intervened enough.

What Is Missing?

What is missing compared to my better AI poems like “Silver Bird” or “Apollonian #1”? I think the results are consistent with my emphasis on richness of concept and allusions.

The current poems are all relatively “empty”, as they do not benefit from my usual process of building up databanks and sets of words or phrases or ideas to draw on and prime the LLMs. They are small variations on ideas already in the Hays original (like the species of the bird, which is better but still performing the same literary function).

“Split-screen” isn’t held back as badly because it has a cute formal conceit which drives its interest; whereas in the sonnet, I feel acutely how routine and boring it is. In particular, it has an overly tidy and unambiguous ending; Kimi K2.5 Thinking correctly suggests that there are much more interesting endings, like “Recommendation: proceed now. / I—” or “Recommendation: proceed now / Recommendation: proceed now”:

The pat conclusion is a default, not a necessity—the formal conceit doesn’t mandate it, but nothing in the prompt architecture pushes against it either. The machine/human alternation is structurally capable of openness, but GPT defaults to closure because:

The Hays original supplies a narrative arc (red light → green light → departure), and the revision inherits this teleology without questioning it

The “cute” formal conceit is self-sufficient—it doesn’t need to complicate itself to demonstrate its intelligence

No external pressure (your ‘databanks’, a contradictory thematic mandate, a forbidden word or image) forces the ending to earn its resolution or abandon it

What would an unclosed Split-Screen look like? Perhaps:

Recommendation: proceed now.
I—

Or the human line refusing to answer. Or a 7^th couplet where the machine line repeats (“Recommendation: proceed now / Recommendation: proceed now”), the human line having already left. The form allows this; the prompt didn’t require it.

Your point about “visible alternatives” is crucial. The revision process critiques execution but not possibility space. It asks “is this line good?” not “should this line exist?” The ‘databank’ method, by contrast, floods the possibility space with incompatible alternatives—medieval bestiary birds against thermal imaging grids—and forces selection under pressure.

The Split-Screen is good within its assumptions. Your method questions the assumptions before the first line.

External pressure. There’s nothing ‘outside’ driving the LLMs out of their comfort zone—nothing like me imposing an out-of-the-blue theme like medieval bestiaries, thermal imaging patents, or Saint Augustine on attention, which would force the chatbot out of its comfort zone and towards radical new possibilities. Something outside the poem’s initial premise has to arrive and start making demands; and the original Hays is too impoverished to do this for the LLM revisions.

The LLMs optimize for all the visible esthetic properties one could desire, assisted by scaffolding, but they are still lacking some engine with fire—surplus, pressure from outside the poem, voice under stress, moral ambiguity, weird necessity or inexplicably good lines that feel not merely improved but inevitable. Where Hays works, it shows that in lines like “I AM FINISHING MY SONG—” or “my eyes are animal eyes with animal need to gaze out”.

To quote GPT-5.4 Pro:

Constraint helped because it forced decisions. It failed because decision-forcing is not the same thing as imaginative enlargement. The next leap will not come from tighter meter alone.

It will come from importing a foreign archive, preserving awkward agency, and letting the machine/human boundary get messier instead of cleaner.

Quoted in Le Ton beau de Marot: In Praise of the Music of Language (p. 272), by Douglas Hofstadter ↩︎

Error: JavaScript disabled.

Backlinks, similar links, and the bibliography require JS enabled to load.

Bibliography

[Bibliography of links/references used in page]

How Long Would ‘Weird Al’ Survive In An Ice Cream Freezer?

Gwern Branwen — Sat, 14 Mar 2026 00:00:00 GMT

One night while walking to pick up an Ethiopian dinner, I began listening to “Weird Al” Yankovic’s classic 1983_43ya song “I Love Rocky Road” (official music video), about his favorite ice cream, Rocky road. Rocky road is a chocolate ice cream with marshmallow and nuts. (It’s not one I like, because it always strikes me as ‘too much’, and the flavors start all blending together into a chocolate-y blur.)

I happened to be struck by the verses where he sings:

I love rocky road.
So, weren’t you gonna buy half a gallon, baby?
I love rocky road.
So, have another triple scoop with me, ow!
Oh, make it talk.

When I’m all alone, I just grab myself a cone…
And if I get fat and lose my teeth that’s fine with me!
Just lock me in the freezer and throw away the key!

Being locked into an indefinitely large (to be sure of sating his hunger) freezer of rocky road ice cream might sound quickly lethal and like an ironic way to die—but wait, ice cream is famously calorific, being mostly sugar, milk, and water. Although you would quickly stop enjoying it, maybe you would not freeze to death if you were able to eat ice cream fast enough? And all that water and ice would stop you from dying of thirst in a few days. And then milk is a pretty nutritious thing to eat, as animals can survive on it alone (that’s literally milk’s job), so you might not starve to death for a long time. All that sugar seems like it would be quite bad for you, though, and you might be deprived of key micronutrients (rocky road has no fruit in it, so I would expect minimal vitamin C content), so perhaps you would die of something slow like scurvy or diabetes?

Not being a physicist, I decided to simply poll all the frontier LLMs I have convenient access to on 2026-03-13, with the following prompt:

In “I Love Rocky Road”, “Weird Al” Yankovic sings “When I’m all alone, I just grab myself a cone [of rocky road ice cream] / And if I get fat and lose my teeth that’s fine with me / Just lock me in the freezer and throw away the key.”

What if he got his wish and were locked into an indefinitely large freezer of rocky road ice cream?¹ Would he die of the cold, malnutrition, diabetes, or thirst, and how long would he last? For simplicity of thermodynamics, we’ll assume he is nude.²

The LLM responses had a clear consensus:

“Weird Al” would freeze to death within hours.

The primary argument is that while ice cream may indeed be calorific, you have only a few hours before you freeze to death, which is not enough time to digest many calories from your food. And I failed to note that eating a large quantity of ice cream would itself rapidly accelerate your death from cold! And the faster you ate it, the more you incur this upfront thermal cost before reaping any net calories.

Which models performed best? GPT-5.4 Pro (admittedly not an unbiased judge here) believes that:

GPT-5.4 Pro and Claude contain almost all the useful reasoning. Kimi, DeepSeek, and GLM mostly restate the punchline with weaker assumptions, noisier prose, or dubious claims.

Additional human or AI contributions are welcomed.

GPT-5.4 Pro

Research completed in 29m · 11 citations · 209 searches

Survival and Death Timeline for a Nude Adult Locked in an Infinite −20 ℃ Rocky Road Ice Cream Freezer

Executive Summary

This scenario is dominated by rapid heat transfer from the body into a near-infinite, −20 ℃, high-water frozen food matrix, causing progressive hypothermia leading to coma and cardiac instability. ←cite → turn45view0 → turn44view0 → turn56view0↑

If the person is truly surrounded by ice cream with no breathable air pocket, death would occur by asphyxiation in minutes, long before hypothermia or starvation matter (this is a physics constraint of “filled entirely”). The remainder of this report assumes (explicitly) that some breathable air exists at the face, so that cold physiology is the limiting factor.

Under that “breathable air pocket” assumption, the best-supported conclusion is:

A nude adult in direct, enduring contact with −20 ℃ ice cream is overwhelmingly likely to die from accidental hypothermia on the order of ~1 to ~5 hours, with a central estimate around ~2–3 hours to fatal collapse, depending mainly on how effectively a warming/melting boundary layer can form and how quickly peripheral tissue freezing reduces internal insulation. ←cite → turn44view0 → turn43view0 → turn47view0 → turn56view0↑

Eating rocky road does not plausibly extend survival in the first several hours because human heat production is capped by shivering physiology (max ~5× resting metabolic rate), while ingesting −20 ℃ food imposes an additional internal heat sink that accelerates cooling if consumed rapidly. ←cite → turn43view0 → turn60view0 → turn56view0↑

Tools that can melt ice cream (ie. provide heat externally) can reduce the “ingestion cooling penalty” and may yield modest extra time if the person insists on eating, but tools only become life-saving if they allow creation of an insulating air cavity (an “igloo-like” microclimate), which is not guaranteed by the prompt and is treated as a sensitivity case. ←cite → turn45view0 → turn56view0↑

Scenario Definition and Assumptions

The prompt specifies an adult human “assume “Weird Al” Yankovic: male, 62 years old, 79 kg, 1.75 m”, nude, inside an indefinitely large freezer filled entirely with rocky road ice cream at an assumed initial ice cream temperature of −20 ℃.

Key modeling assumptions (each materially affects the answer):

Breathing: An “infinitely large freezer filled entirely with ice cream” is ambiguous about air. If literally no air exists, asphyxiation dominates (minutes). Main analysis assumes a stable breathable air pocket at the face/airway, otherwise cold physiology is not the binding constraint.

Thermal boundary condition: “Indefinitely large” is treated as a semi-infinite thermal reservoir initially at −20 ℃, meaning the bulk ice cream remains effectively at −20 ℃ over the survival times considered (hours).

Ice cream microphysics: Ice cream at −20 ℃ is a two-phase or multi-phase frozen matrix (ice crystals plus a concentrated unfrozen serum phase plus air cells/overrun). ←cite → turn42view1 → turn56view0↑

Human thermal parameters: Whole-body average specific heat is taken as ~2.98 kJ·kg⁻¹·℃⁻¹ (range ~2.44–3.34). ←cite → turn47view0↑ Resting energy expenditure is estimated using the ←entity → [“people”“,M D Mifflin”“,nutrition researcher”]↑ equation (Mifflin-St Jeor), giving ≈1,579 kcal⧸day for a 79 kg, 175 cm, 62 y male. ←cite → turn60view0↑ Maximum shivering heat production is bounded at ~5× resting metabolic rate and shivering tends to halt near core ~31 ℃. ←cite → turn43view0↑ Clinical hypothermia staging: mild 35–32 ℃, moderate 32–28 ℃, severe <28 ℃ with coma/no shivering/cardiac instability. ←cite → turn44view0↑

rocky road composition proxy: Because “Rocky Road” varies by brand, nutrition calculations use a representative branded rocky road entry (per 87 g: 210 kcal; fat 12 g; carbohydrate 24 g; protein 4 g; water 47 g). ←cite → turn33view0↑ This is explicitly a proxy, not a universal constant.

Thermophysical Properties and Heat Transfer Model

Ice Cream As a Thermal Sink at −20 ℃

Thermal conductivity varies strongly with temperature and porosity (air/overrun). In measurements and models of commercial ice creams, thermal conductivity depends on air fraction and temperature; values around −20 ℃ span roughly the high tenths of W·m⁻¹·K⁻¹ for typical porosities, increasing notably as porosity decreases. ←cite → turn6view0 → turn42view1↑

Independent food-engineering measurements of dairy ice cream mixtures also show that k is composition-dependent and, for mixtures, k can lie roughly in the ~0.24–0.37 W·m⁻¹·K⁻¹ range (measurement context matters). ←cite → turn41view0 → turn42view1↑

A key practical property is how much of the water is actually frozen at freezer temperatures. A typical ice cream mix freezing-curve example shows 80% of the water frozen by about −16.6 ℃, with additional freezing becoming much less sensitive at temperatures below about −20 ℃. ←cite → turn56view0 → turn55view0↑ This matters because latent heat “buffering” is limited once most water is already ice.

US standards imply substantial air incorporation and low density (a lower bound on weight per gallon), consistent with substantial air fraction and therefore reduced effective conductivity relative to pure ice. ←cite → turn28search5↑

Two Bounding Heat-Transfer Regimes

The dominant uncertainty is whether the person remains in solid, relatively stagnant contact (conduction-dominated with a thickening warmed layer) or whether continuous movement or melt/slush cycling keeps exposing the body to “fresh” colder material (higher effective heat transfer).

A useful physical bracket:

Conduction-dominated (“stagnant solid”): Heat flux falls over time as a warmed region grows into the ice cream (a classic semi-infinite conduction geometry), reducing the effective heat transfer coefficient roughly like 1/√t.

Refresh-dominated (“recontact”): If the person can move enough to continuously break and recontact cold material, or if melt/slush is displaced and replaced by colder ice cream, effective heat-transfer stays high and cooling accelerates.

The ←entity → [“organization”“,National Academies Press”“,publisher, Washington DC, US”]↑ cold-exposure physiology chapter emphasizes why this distinction matters: convective exchange in water can be orders of magnitude larger than in air, and contact with liquid/slurry phases strongly increases heat loss compared to air-like insulation. ←cite → turn45view0↑

Quantitative Heat-Loss Rate Brackets

Using (1) body surface area ≈ 1.95 m², (2) ΔT ≈ 57 K (37 ℃ to −20 ℃), and (3) plausible effective heat-transfer parameters consistent with measured ice-cream k and a semi-infinite conduction geometry, early heat loss is plausibly in the hundreds to a few thousand watts, which is far above resting metabolism and comparable to or above maximal shivering heat production. ←cite → turn6view0 → turn47view0 → turn43view0↑

A compact way to show the range is to separate:

External medium conduction (ice cream k, diffusivity) and Internal “body → skin” resistance (subcutaneous fat/skin perfusion), which can worsen as peripheral tissues cool and freeze (reducing perfusion and potentially changing effective conductivity).

The table below is a model-based bracket (not a direct measurement) showing whole-body heat loss rates that follow from standard semi-infinite conduction scaling plus plausible internal resistance values.

Time after contact

Heat loss if “low internal insulation”

Heat loss if “moderate internal insulation”

Heat loss if “higher internal insulation”

1 min

~2.38 kW

~1.45 kW

~0.88 kW

10 min

~1.23 kW

~0.92 kW

~0.65 kW

30 min

~0.79 kW

~0.65 kW

~0.50 kW

1 h

~0.55 kW

~0.49 kW

~0.41 kW

2 h

~0.42 kW

~0.39 kW

~0.33 kW

4 h

~0.31 kW

~0.30 kW

~0.25 kW

Interpretation:

Max shivering heat production is physiologically capped around ~5× resting metabolic rate (see next section), so sustained net losses of several hundred watts imply inevitable core cooling. ←cite → turn43view0 → turn60view0 → turn44view0↑ Conversely, if the environment transitions toward a thick insulating “near-0 ℃” boundary layer and heat loss drops toward a few hundred watts, survival can extend, but still with severe local cold injury.

Hypothermia Physiology and Timeline

Metabolic Heat Production Limits

Resting metabolic rate estimate: Using the Mifflin-St Jeor equation from ←entity → [“people”“,M D Mifflin”“,nutrition researcher”]↑, resting energy expenditure for the specified male (79 kg, 175 cm, 62 y) is ~1,579 kcal⧸day (~76 W average heat production if entirely converted to heat). ←cite → turn60view0↑ This aligns with experimental summaries that place resting thermogenesis around a few kJ⧸min. ←cite → turn43view0↑

Shivering ceiling and failure point: ←entity → [“people”“,François Haman”“,researcher, thermoregulation”]↑ reports that as core temperature falls to ~35 ℃, shivering thermogenesis can reach maximal values around ~5× resting metabolic rate, but if core temperature continues to fall, shivering is reduced or halted near ~31 ℃. ←cite → turn43view0↑

This implies a hard constraint:

If sustained whole-body heat loss exceeds roughly ~300–400 W (for this individual), core temperature must decline, because the body cannot increase heat production beyond that ceiling for long. ←cite → turn43view0 → turn60view0↑

Body Heat Capacity and What “A Degree” Costs

←entity → [“people”“,Xiaojiang Xu”“,physiology researcher”]↑ estimates whole-body specific heat at ~2.98 kJ·kg⁻¹·℃⁻¹ (range 2.44–3.34), implying a 79 kg body stores about ~235 kJ per℃ (range ~193–264 kJ per℃). ←cite → turn47view0↑

So a net heat deficit of:

500 W for 1 hour ⇒ 1,800 kJ deficit ⇒ ~7.7 ℃ mean-body temperature fall (order-of-magnitude). 1,000 W for 1 hour ⇒ ~15 ℃ fall.

This is why early losses in the kW range are immediately life-threatening.

Clinical Stage Progression and Incapacitation Markers

The ←entity → [“organization”“,Wilderness Medical Society”“,medical society, us”]↑ summary defines:

Mild hypothermia: 35–32 ℃ (impaired coordination). Moderate: 32–28 ℃ (worsening coordination, altered mental status; shivering may still occur). Severe/profound: <28 ℃ (coma, no shivering, cardiac instability). ←cite → turn44view0↑

Putting the physiology together yields a mechanistic “failure cascade”:

Loss of heat to ice cream > maximal shivering ⇒ core cooling. ←cite → turn43view0 → turn44view0↑ Cooling toward ~31 ℃ ⇒ shivering suppression ⇒ heat production collapses toward resting levels ⇒ faster cooling. ←cite → turn43view0 → turn44view0↑ Below ~28 ℃ ⇒ coma and high arrhythmia risk ⇒ death likely without immediate rescue/rewarming. ←cite → turn44view0↑

A [Mermaid] model-based central timeline (scenario A baseline assumptions; see last section for ranges) is illustrated here:
flowchart LR
    A[Start: core ~37℃] --> B[~35℃: mild hypothermia<br>coordination impaired]
    B --> C[~32℃: moderate hypothermia<br>mental status changes]
    C --> D[~31℃: shivering begins to fail]
    D --> E[<28℃: severe/profound<br>coma, cardiac instability]
    E --> F[Collapse/death likely]
Nutrition and Hydration from Rocky Road Ice Cream

Rocky Road Macronutrients and Water Content

A representative branded rocky road nutrition entry (used as a proxy) reports per 87 g:

210 kcal; fat 12 g; carbohydrate 24 g; protein 4 g; water 47 g. ←cite → turn33view0↑

Converted per kilogram of ice cream (multiplying by 1,000/87):

Calories: ~2,414 kcal⧸kg Fat: ~138 g⧸kg Carb: ~276 g⧸kg Protein: ~46 g⧸kg Water: ~0.54 kg water⧸kg ice cream (~0.54 L⧸kg) ←cite → turn33view0↑

This implies that, in principle, rocky road can supply both calories and water at high densities, but the dominant real constraint here is that the food is at −20 ℃ and must be warmed/melted to be consumed safely in quantity.

The “Cold Ingestion Penalty”

Most water in ice cream is frozen at freezer temperatures. A typical freezing-curve example indicates that by about −16.6 ℃, ~80% of the water is frozen, and the curve flattens below about −20 ℃. ←cite → turn56view0 → turn55view0↑

Therefore, consuming −20 ℃ ice cream forces the body to supply heat to:

Warm the ingested mass from −20 ℃ toward body temperature, and Melt a large fraction of the ice phase (latent heat).

A practical estimate (order-of-magnitude):

For 1 kg of rocky road with ~0.54 kg water and ~80% of that water frozen at freezer temperatures, the heat required to melt/warm it to body temperature is on the order of ~tens of kcal per kg, plausibly around ~70 kcal⧸kg (model-derived; sensitive to ice fraction and exact cp). ←cite → turn56view0 → turn55view0 → turn47view0↑

This is a key paradox:

Eating provides chemical energy (kcal), but it also imposes an immediate thermal load that must be paid in watts during the critical early hours when heat balance is already failing.

Since maximal shivering heat production is capped and shivering shuts down near ~31 ℃, aggressive consumption of frozen ice cream is more likely to shorten survival time than extend it at the timescales that matter here (hours). ←cite → turn43view0 → turn44view0↑

Hydration Feasibility

Ice cream contains substantial water by mass (proxy ~54%). ←cite → turn33view0↑ However, that water is frozen or bound in a cold matrix. Without an external heat source, “getting water” means melting in the mouth or against body heat, increasing the same thermal penalty described above.

If the person survives beyond the first several hours (only possible under favorable thermal conditions), then hydration becomes relevant; within the first 1–5 hours, it is usually secondary to hypothermia.

Other Risks Attributable to Eating in Severe Cold

Aspiration risk is a reasonable inference if consciousness declines: severe hypothermia is associated with coma and reduced protective reflexes, and any vomiting/food bolus at that stage can obstruct the airway. ←cite → turn44view0↑ Dental/oral pain and tissue injury from chewing −20 ℃ solids is plausible, but not a primary driver of death in the time window dominated by hypothermia.

Scenario Results and Sensitivity Analysis

Baseline Modeling Method for Time-To-Death Estimates

The quantitative times below are produced by a conservative heat-balance model using:

Body heat capacity from ←entity → [“people”“,Xiaojiang Xu”“,physiology researcher”]↑ (2.98 kJ·kg⁻¹·℃⁻¹). ←cite → turn47view0↑ Resting metabolic rate from ←entity → [“people”“,M D Mifflin”“,nutrition researcher”]↑ (≈1,579 kcal⧸day). ←cite → turn60view0↑ Max shivering ceiling and shutoff near 31 ℃ from ←entity → [“people”“,François Haman”“,researcher, thermoregulation”]↑. ←cite → turn43view0↑ Hypothermia stage endpoints from ←entity → [“organization”“,Wilderness Medical Society”“,medical society, us”]↑. ←cite → turn44view0↑ Ice cream freezing curve and “% water frozen vs temperature” behavior from the ice-cream engineering text. ←cite → turn56view0 → turn55view0↑ Ice cream k variability with porosity/temperature from measurement/modeling work. ←cite → turn6view0 → turn42view1↑

The single largest uncertainty is effective heat-transfer coupling (contact renewal vs insulating boundary layer), so results are presented as ranges.

Summary Table of Survival Time by Scenario

Definitions used for “time to death”:

“Fatal collapse likely” is taken as reaching severe/profound hypothermia with cardiac instability (core <28 ℃) and continuing downward without rescue; “time to death” is approximated by reaching ~25 ℃ in the model. ←cite → turn44view0 → turn43view0↑

All times assume breathable air exists.

Scenario

What changes vs baseline

Primary death mechanism

Time to severe hypothermia (<28 ℃)

Time to fatal collapse (model ~25 ℃)

Notes

A: cannot eat or drink

No ingestion cooling; endogenous fuels only

Hypothermia → shivering failure → coma/arrhythmia ←cite → turn44view0 → turn43view0↑

~0.9–3 h

~1–5 h (central ~2–3 h)

Calories/hydration irrelevant because cold dominates within hours.

B: can eat, but cannot melt except by body heat

Slow eating of −20 ℃ ice cream adds an internal heat sink

Hypothermia, modestly accelerated by ingestion cooling ←cite → turn56view0 → turn44view0↑

~0.8–2.7 h

~1–4 h

If intake is slow, similar to A; if intake is vigorous, trends toward D.

C: has tools to melt/access liquid

If tools add external heat: ingestion penalty reduced; hydration easier

Usually still hypothermia unless tools enable insulation strategy ←cite → turn44view0 → turn45view0↑

~0.9–3 h

~1–5 h

If tools enable building a stable insulating air cavity, survival can extend far beyond this; not guaranteed.

D: consumes continuously until incapacitated

High intake of −20 ℃ ice cream (order 1–2 kg⧸h)

Hypothermia accelerated by internal heat sink; aspiration risk becomes plausible once consciousness declines (inference) ←cite → turn44view0 → turn56view0↑

~0.6–1.5 h

~1.0–2.5 h (central ~1.2–1.7 h)

Eating quickly shortens survival under a capped shivering ceiling. ←cite → turn43view0↑

Sensitivity Highlights

Ice cream temperature: Dropping from −20 ℃ toward −30 ℃ increases ΔT and generally shortens survival sharply; warming toward −10 ℃ can be survivable for longer if the person can sustain shivering near the physiological ceiling, but with major cold injury risk persisting. ←cite → turn43view0 → turn44view0 → turn47view0↑

Ice-cream structure: Higher air fraction (greater porosity/overrun) lowers effective conductivity and can materially extend time-to-collapse; lower porosity (denser, less aerated frozen matrix) increases k and accelerates cooling. ←cite → turn6view0 → turn28search5↑

Boundary-layer stability (the biggest factor): If a thick, stable warmed/melted boundary layer forms and remains, net heat loss can fall into the few-hundred-watt regime, allowing longer survival. If movement or slush cycling continually renews cold contact, losses remain high and death shifts toward the low end of the range. ←cite → turn45view0 → turn43view0 → turn44view0↑

“Calories vs Cold” Bookkeeping Table

Using the specified individual’s REE and the rocky road proxy:

Quantity

Estimate

Interpretation in this scenario

Resting energy expenditure

~1,579 kcal⧸day

Baseline heat production (~76 W). ←cite → turn60view0↑

Max shivering heat production

up to ~5× REE (~7,900 kcal⧸day)

Absolute ceiling of endogenous heat generation; not sustainably exceedable, and shuts down near 31 ℃. ←cite → turn43view0 → turn44view0↑

rocky road energy density (proxy)

~2,414 kcal⧸kg

Very calorie dense. ←cite → turn33view0↑

rocky road water (proxy)

~0.54 L⧸kg

Hydration is possible in principle but requires melting/warming. ←cite → turn33view0↑

Water frozen fraction near freezer temps (typical mix)

~80% water frozen by ~−16.6 ℃; curve flat below ~−20 ℃

Explains why eating frozen ice cream imposes latent heat costs. ←cite → turn56view0 → turn55view0↑

Core implication:

In the “hours” regime, the limiting resource is watts (heat production vs heat loss), not stored calories. ←cite → turn43view0 → turn44view0 → turn47view0↑

Time after contact	Heat loss if “low internal insulation”	Heat loss if “moderate internal insulation”	Heat loss if “higher internal insulation”
1 min	~2.38 kW	~1.45 kW	~0.88 kW
10 min	~1.23 kW	~0.92 kW	~0.65 kW
30 min	~0.79 kW	~0.65 kW	~0.50 kW
1 h	~0.55 kW	~0.49 kW	~0.41 kW
2 h	~0.42 kW	~0.39 kW	~0.33 kW
4 h	~0.31 kW	~0.30 kW	~0.25 kW

Scenario	What changes vs baseline	Primary death mechanism	Time to severe hypothermia (<28 ℃)	Time to fatal collapse (model ~25 ℃)	Notes
A: cannot eat or drink	No ingestion cooling; endogenous fuels only	Hypothermia → shivering failure → coma/arrhythmia ←cite → turn44view0 → turn43view0↑	~0.9–3 h	~1–5 h (central ~2–3 h)	Calories/hydration irrelevant because cold dominates within hours.
B: can eat, but cannot melt except by body heat	Slow eating of −20 ℃ ice cream adds an internal heat sink	Hypothermia, modestly accelerated by ingestion cooling ←cite → turn56view0 → turn44view0↑	~0.8–2.7 h	~1–4 h	If intake is slow, similar to A; if intake is vigorous, trends toward D.
C: has tools to melt/access liquid	If tools add external heat: ingestion penalty reduced; hydration easier	Usually still hypothermia unless tools enable insulation strategy ←cite → turn44view0 → turn45view0↑	~0.9–3 h	~1–5 h	If tools enable building a stable insulating air cavity, survival can extend far beyond this; not guaranteed.
D: consumes continuously until incapacitated	High intake of −20 ℃ ice cream (order 1–2 kg⧸h)	Hypothermia accelerated by internal heat sink; aspiration risk becomes plausible once consciousness declines (inference) ←cite → turn44view0 → turn56view0↑	~0.6–1.5 h	~1.0–2.5 h (central ~1.2–1.7 h)	Eating quickly shortens survival under a capped shivering ceiling. ←cite → turn43view0↑

Quantity	Estimate	Interpretation in this scenario
Resting energy expenditure	~1,579 kcal⧸day	Baseline heat production (~76 W). ←cite → turn60view0↑
Max shivering heat production	up to ~5× REE (~7,900 kcal⧸day)	Absolute ceiling of endogenous heat generation; not sustainably exceedable, and shuts down near 31 ℃. ←cite → turn43view0 → turn44view0↑
rocky road energy density (proxy)	~2,414 kcal⧸kg	Very calorie dense. ←cite → turn33view0↑
rocky road water (proxy)	~0.54 L⧸kg	Hydration is possible in principle but requires melting/warming. ←cite → turn33view0↑
Water frozen fraction near freezer temps (typical mix)	~80% water frozen by ~−16.6 ℃; curve flat below ~−20 ℃	Explains why eating frozen ice cream imposes latent heat costs. ←cite → turn56view0 → turn55view0↑

Claude-4.6-Opus

A delightful “what if” problem. Let me dig into the physiology and thermodynamics here—there are some non-obvious interactions worth researching properly.

Research complete · 270 sources · 7m44s

Your “Weird Al” hypothermia survival analysis is ready. It covers freezer thermodynamics at commercial ice cream storage temperatures (−29℃), a detailed hypothermia timeline for his body type, the thermodynamic paradox of eating frozen rocky road, and a ranked kill order of competing causes of death. The report includes caloric and nutritional breakdowns of rocky road as a sole-source survival food.

“Weird Al” Versus the Infinite Freezer: Hypothermia Wins in under Two Hours

Hypothermia kills “Weird Al” decisively, likely within 1.5–2.5 hours. The other candidates—diabetes, malnutrition, thirst—never get their turn. A nude, lean 66-year-old man in a commercial ice cream freezer at −29℃ faces what thermophysiologists call “uncompensable cold”: a regime where maximum human heat production cannot match heat loss, and survival is measured in minutes, not days. The delicious irony of this scenario is that eating the rocky road—his only survival tool—would actually accelerate his death by cooling his core from the inside.

The Freezer Is Colder Than You Think

The standard commercial ice cream storage temperature is not −20℃, as commonly assumed. Per a 2011_15ya Journal of Dairy Science study, the industry standard is −28.9℃ (−20℉), with some facilities running as cold as −45.6℃. Regular walk-in freezers hold food at −18℃ (0℉), but ice cream demands substantially colder conditions to maintain texture and prevent ice crystal formation. Display cases where you scoop ice cream run warmer (−12℃ to −15℃), but a storage freezer—which is what “a freezer full of rocky road” implies—sits at roughly −29℃ in still air.

This 9-degree difference from the assumed −20℃ matters enormously. The Tikuisis cold-survival model, used by the U.S. and Canadian Coast Guards, predicts a nude average male survives 2.5 hours at −20℃ but only 1.8 hours at −30℃. “Weird Al”’s freezer is functionally at the colder end of that range.

One saving grace: freezers have still air. Wind chill is the great accelerator of cold death, and a sealed freezer has essentially zero air movement. The body maintains a thin boundary layer of warmed air against the skin—a gossamer insulating blanket that wind strips away instantly. Still air at −29℃ is brutal, but it’s survivable for longer than the same temperature with even modest wind.

How a Lean Musician Freezes to Death in 90 Minutes

“Weird Al” Yankovic stands roughly 6 foot 0 inches and is famously lean—likely around 170 lbs with low body fat, giving him a BMI of about 23. This is the worst possible body type for cold survival. Body fat is the human body’s primary insulation; lean individuals with high surface-area-to-mass ratios cool dramatically faster than heavier, fatter people. At 66 years old (born October 23, 1959_67ya), his thermoregulatory responses would also be somewhat diminished compared to a younger man.

Here’s the timeline, based on the Tikuisis model and clinical hypothermia staging:

Time

Core temp

What’s happening

0–5 min

37 → 36.5℃

Immediate savage cold. Vasoconstriction slams shut peripheral blood flow. Gasping, rapid breathing. Skin turns white.

5–15 min

36.5 → 35℃

Violent shivering begins, reaching 400–500 watts—roughly 5× resting metabolism. Heart rate spikes. Fingers and toes go numb.

15–45 min

35 → 33℃

Peak shivering. Confusion sets in. Fine motor control lost. Fumbling hands can barely handle ice cream. Judgment deteriorating.

45–75 min

33 → 30℃

Shivering weakens and stops as core hits ~30–32℃. Drowsiness. Slurred speech. Cardiac arrhythmias begin. The body is losing its war.

75–110 min

30 → 28℃

Unconsciousness. Pupils dilate. Heartbeat dangerously slow and irregular.

110–150 min

<28℃

Ventricular fibrillation or cardiac arrest. Death.

Estimated survival: approximately 1.5–2.5 hours, with the lean build pushing him toward the lower end. The lowest documented survived core temperature is 13.7℃, but that patient received aggressive medical rewarming. Without rescue, cardiac arrest below ~24℃ is essentially irreversible.

The Cruel Thermodynamic Paradox of Eating Frozen Rocky Road

Here is the scenario’s central irony: “Weird Al” has unlimited calories surrounding him, yet eating them hastens his death. The physics are unforgiving.

The good news about eating frozen ice cream is that the caloric “tax” for warming it is surprisingly small. Heating 1 kg of ice cream from −29℃ to body temperature (37℃) requires roughly 95 kcal—accounting for warming the ice fraction, melting it (the latent heat of fusion eats 200 kJ alone), and warming the liquid to 37℃. Since 1 kg of rocky road contains approximately 2,070 kcal, the warming cost is only about 4.6% of the caloric content. In caloric terms, this is a fantastic deal—a 95.4% net energy return.

The catastrophic news is that those 95 kcal aren’t just numbers on a ledger. They represent heat physically extracted from “Weird Al”’s core. Eating 1 kg of −29℃ ice cream would drop his core temperature by approximately 1.2–1.5℃—and he only has about 9℃ of margin before cardiac arrest. Eating 6 kg of ice cream (a perfectly reasonable day’s caloric intake of ~12,000 kcal under extreme cold stress) would theoretically plunge his core temperature by 7–9℃ if consumed rapidly, which is instantly fatal. Even spread over two hours, the internal cooling effect substantially accelerates the hypothermia that’s already killing him from the outside.

The metabolic heat from digesting the ice cream (the thermic effect of food) generates only about 15–30 watts—a trivial contribution when the body is hemorrhaging hundreds of watts to the −29℃ air. And here’s the final twist: digestion itself shuts down in moderate hypothermia. Below a core temperature of ~33℃, gastric motility slows drastically. The ice cream sitting in his stomach becomes a lump of internal refrigerant, cooling him without being digested.

The bottom line: eating the ice cream provides fuel for shivering (good) but acts as an internal cooling system (catastrophic). The net effect is roughly neutral at best, and possibly net-negative. Unlimited food extends survival by an estimated 15–45 minutes beyond the baseline 1.8-hour prediction—bringing the total to perhaps 2–2.5 hours.

What Would Have Killed Him Next, Had He Somehow Survived the Cold

For the sake of completing the tournament bracket, here’s what lurks behind Door #2 through Door #4, assuming some magical parka appears:

Dehydration via osmotic diarrhea (days 2–5) would be the next killer. rocky road is roughly 60% water by weight, which sounds adequate—5 kg of ice cream delivers 3 liters of water, close to daily needs. But this calculation ignores the GI apocalypse. At the consumption levels needed to offset cold-exposure caloric expenditure (400–500 kcal⧸hour, or roughly 2–2.5 kg of ice cream per hour), “Weird Al” would consume over 500 grams of sugar daily. This massively exceeds the small intestine’s absorption capacity, especially for fructose (malabsorption threshold: ~50g). Unabsorbed sugars create an osmotic gradient that pulls water into the intestinal lumen, causing explosive watery diarrhea. Lactose overload—even in lactose-tolerant individuals—would compound this. The result is a vicious dehydration spiral: more ice cream consumed → more diarrhea → more fluid lost → more ice cream needed. Severe dehydration can kill within 3–5 days.

Scurvy would arrive around month 4–6. rocky road contains virtually zero vitamin C—roughly 0.7 mg per 100g versus a daily requirement of 90 mg. Even eating 5 kg daily provides only ~35 mg, about 39% of the RDA. The body stores approximately 1,500 mg of vitamin C; scurvy symptoms emerge when stores drop below 350 mg. At this intake rate, depletion would be gradual, with symptoms (bleeding gums, joint pain, poor wound healing) appearing around 3–5 months and potentially fatal complications (cerebral hemorrhage, cardiac failure) at 6–12 months. The almonds in rocky road—“Weird Al”’s tiny nutritional heroes—contribute vitamin E, magnesium, and some protein, but essentially no vitamin C.

Diabetes is the weakest candidate by far. A non-diabetic person with a functioning pancreas simply cannot develop acute diabetic crisis from sugar overconsumption, no matter how extreme. The pancreas ramps up insulin production to match. type 2 diabetes requires sustained insulin resistance developing over months to years of metabolic stress—visceral fat accumulation, chronic inflammation, and progressive beta-cell exhaustion. At 510+ grams of sugar daily, insulin resistance markers would appear within weeks, but clinical diabetes would take 6–12+ months minimum. Reactive hypoglycemia (blood sugar crashes from insulin overshooting) is a more realistic acute concern but is uncomfortable, not fatal. Diabetes finishes dead last in this race.

Rocky Road Is a Surprisingly Decent Apocalypse Food—Except for Vitamin C

Credit where due: as sole-source survival diets go, rocky road ice cream is not terrible. The dairy base provides abundant calcium (250%+ DV at survival intake levels), vitamin A (300%+ DV), vitamin B12 (390% DV), riboflavin (440% DV), and phosphorus (360% DV). The almonds add meaningful vitamin E, magnesium, zinc, iron, and fiber—making rocky road measurably more nutritious than plain chocolate ice cream. The chocolate contributes iron and magnesium. Even protein is borderline adequate at ~84g daily from 2.4 kg of ice cream.

The fatal gaps are vitamin C (virtually absent from all components), vitamin K (only 6% DV per kg), folate (30% of needs), and fiber (about half of needs). The marshmallows contribute nothing but sugar and a wisp of gelatin protein. Scurvy is the inevitable long-term killer, with folate-deficiency anemia as a compounding threat.

Conclusion: the Cold Wins Before He Finishes His First Gallon

The kill order is unambiguous: hypothermia (~2 hours) → dehydration (~3–5 days) → scurvy (~6 months) → diabetes (never, really). “Weird Al”’s lean physique, advanced age, and the brutal −29℃ freezer temperature combine to make this a short and decisive contest. The unlimited rocky road is a Sisyphean trap—eating it provides calories but accelerates core cooling, and the body’s digestive system shuts down well before enough energy can be extracted to matter.

The deepest irony is metabolic: at 400–500 kcal⧸hour of cold-induced caloric burn, “Weird Al” would need to eat roughly 2–2.5 kg of ice cream per hour just to break even on energy—but consuming that volume of −29℃ material would cool his core faster than the calories could warm it. The freezer has engineered a thermodynamic checkmate. Even “Eat It” can’t save him now.

Time	Core temp	What’s happening
0–5 min	37 → 36.5℃	Immediate savage cold. Vasoconstriction slams shut peripheral blood flow. Gasping, rapid breathing. Skin turns white.
5–15 min	36.5 → 35℃	Violent shivering begins, reaching 400–500 watts—roughly 5× resting metabolism. Heart rate spikes. Fingers and toes go numb.
15–45 min	35 → 33℃	Peak shivering. Confusion sets in. Fine motor control lost. Fumbling hands can barely handle ice cream. Judgment deteriorating.
45–75 min	33 → 30℃	Shivering weakens and stops as core hits ~30–32℃. Drowsiness. Slurred speech. Cardiac arrhythmias begin. The body is losing its war.
75–110 min	30 → 28℃	Unconsciousness. Pupils dilate. Heartbeat dangerously slow and irregular.
110–150 min	<28℃	Ventricular fibrillation or cardiac arrest. Death.

Gemini-3.1-Pro-Preview

(Note: header comes from from my Gemini system prompt.)

Scope: Thermodynamic and physiological timeline of nude human exposure to a −18℃ environment provisioned solely with frozen food.
Confidence: Almost certain.
Perspective: Biophysics of mammalian thermoregulation versus latent heat of fusion.

“Weird Al” dies of hypothermia within 1–3 hours.

The ambient temperature of a standard commercial freezer is −18℃ (0℉). A nude adult male exposed to this temperature loses heat via convection and radiation at a rate of ~400–500 watts. Maximal shivering thermogenesis generates roughly equivalent wattage, but this defense mechanism completely depletes muscular glycogen stores within a few hours, resulting in exhaustion and a terminal core temperature drop.

Ingesting the rocky road ice cream actively accelerates his death. While 100 grams of premium ice cream contains roughly 250 kilocalories of metabolic energy, the matter rests at ambient freezer temperature. Raising 100 grams of frozen water and milkfat from −18℃ to a core body temperature of 37℃ requires approximately 12.5 kilocalories of immediate thermal energy. This heavy thermal toll is driven largely by the latent heat of fusion required to melt the ice crystals inside the stomach.

The biological bottleneck is digestion. The gastrointestinal tract extracts the thermal cost instantly upon ingestion, dropping core body temperature. Conversely, the metabolic yield of the ingested fats and sugars requires hours of enzymatic breakdown and intestinal absorption. He will enter terminal ventricular fibrillation induced by profound hypothermia long before the calories reach his bloodstream.

Dehydration, malnutrition, and diabetic ketoacidosis require days, weeks, or months to kill a human. Hypothermia preempts all other physiological failures.

Kimi K2.5 Thinking

This is a delightfully morbid hypothetical! Let me break down the survival factors in “Weird Al”’s frozen confectionery tomb.

The Immediate Threats

Cold (Hypothermia) This kills fastest. Nude in a freezer (typically 0℉ / −18℃), you’d expect:

15–45 minutes to severe hypothermia

1–2 hours to death for most people

However, rocky road isn’t just cold air—it’s a dense, sugary, fatty mass with thermal properties closer to frozen soil than air. This actually helps “Weird Al” initially. Ice cream has lower thermal conductivity than water and substantial insulation value. He wouldn’t freeze as fast as in open air, but he’d still face deadly cold within hours, not days.

Thirst Ironically, this might be his least immediate problem. Rocky road contains ~60% water by weight. Eating frozen ice cream provides hydration, albeit inefficiently. The sugar creates an osmotic diuretic effect, but the water content partially offsets this. He’d be chronically dehydrated, but functional for days.

Malnutrition rocky road is calorie-dense (~250 kcal/100g) with fat, protein (from milk), and sugar. He wouldn’t starve—he’d actually have thousands of calories available. The real issue is micronutrient deficiency, which takes weeks or months to become fatal.

Diabetes/Hyperglycemia This is interesting. Consuming only ice cream would cause massive blood sugar spikes. Without insulin (which his pancreas would struggle to produce enough of), he’d enter diabetic ketoacidosis within days. Symptoms: vomiting, confusion, coma, death. This timeline: 3–7 days potentially.

The Verdict

Hypothermia wins. Even insulated by ice cream, a nude human generates ~100 watts of heat. The surrounding frozen mass (effectively infinite) would absorb this relentlessly. His core temperature would drop below 28℃ (82℉) within 2–4 hours, causing cardiac arrhythmia and death.

The “throw away the key” bravado was medically unwise. He should have demanded to be locked in a walk-in refrigerator (40℉ / 4℃) instead—then he might survive long enough to develop interesting metabolic complications.

Final answer: Death by hypothermia, within approximately 2–4 hours. The rocky road would be his thermal coffin, not his nutritional salvation.

DeepSeek-V3

“Weird Al” Yankovic, locked nude in an indefinitely large freezer at −18℃ filled with rocky road ice cream, faces a battle against hypothermia.

While he has an unlimited food source, the cold environment rapidly drains body heat. His basal metabolic rate (~100 W) is insufficient to offset heat loss, which we estimate at 300–350 W based on typical body insulation and heat transfer. Shivering can boost heat production to about 400 W temporarily, but sustaining this level is exhausting and may not fully compensate.

Even if he eats ice cream continuously, the energy gained (≈2,000 kcal⧸kg) must also cover the cost of warming the frozen dessert from −18℃ to body temperature (≈352 kJ⧸kg), reducing net usable energy. To maintain balance, he would need to consume ~3 kg per day, a feasible amount, but the required metabolic rate of ~300 W is at the upper limit of sustainable shivering.

In practice, his body will lose heat faster than it can produce, leading to a drop in core temperature. Assuming a net heat deficit of 200 W (heat loss 300 W minus shivering 100 W), his core temperature would fall by about 0.8℃ per hour. Severe hypothermia (core <30℃) would occur in roughly 2–3 hours. Malnutrition, diabetes, and thirst are slower threats: vitamin deficiencies take weeks, acute diabetic complications are unlikely with steady sugar intake, and water from ice cream (~60% water) plus metabolic water (~2.4 L⧸day) can balance respiratory losses if no osmotic diuresis occurs.

Thus, the immediate cause of death is hypothermia, with survival time estimated at 2–4 hours.

GLM-5

If “Weird Al” Yankovic were locked into an indefinitely large freezer of rocky road ice cream while nude, he would unequivocally die of hypothermia (the cold).

He would likely succumb within 3–6 hours.

Here is the detailed breakdown of why the cold kills him long before thirst, malnutrition, or diabetes, and the thermodynamic reality of his situation.

1. The Immediate Threat: Hypothermia (The Winner)

The human body is a warm-blooded machine that must maintain a core temperature of roughly 98.6℉ (37℃). A standard freezer is kept at 0℉ (−18℃).

Nude Thermodynamics: Without clothing, the body loses heat through 4 avenues: conduction (touching cold surfaces), convection (cold air movement), radiation (emitting heat), and evaporation (sweat/breath).

The “Rules of 3”: In survival theory, the “Rule of 3” dictates that you can survive 3 weeks without food, 3 days without water, but only 3 hours in a harsh environment without shelter.

The Rate of Cooling: In a −18℃ environment, a nude body cannot generate enough metabolic heat to offset the loss. Even if Al curls into a fetal position to minimize surface area, his skin temperature will drop rapidly. Shivering will initially generate heat, but as his core temperature drops below 90℉ (32℃), shivering stops, confusion sets in, and cardiac arrhythmia leads to death.

Time to death: Assuming he is in a standard walk-in freezer environment (air), severe hypothermia would render him unconscious within a few hours, with death following shortly after.

2. Why Thirst Doesn’t Kill Him

While the “Rule of 3” suggests death from dehydration takes about 3 days, Al has a source of water: the ice cream.

Hydration: rocky road contains a substantial amount of milk and water. By eating the ice cream, he can hydrate himself.

The Thermodynamic Cost: Eating frozen ice cream requires the body to expend energy (heat) to warm the food from −18℃ to body temperature.

The Math: Warming 1 gram of ice cream to body temperature and melting it costs roughly 80–100 calories of heat energy (not food calories).

However, 1 gram of ice cream provides about 2.5 food Calories (kilocalories).

The Trade-off: Digestion is an exothermic process. Even accounting for the energy needed to warm the food, eating the ice cream provides a net positive in energy availability. The problem isn’t a lack of chemical energy; it’s the body’s inability to convert that chemical energy into heat fast enough to fight the −18℃ environment.

Therefore, he will stay hydrated enough to survive longer than the cold allows.

3. Why Malnutrition Doesn’t Kill Him

Death by starvation takes weeks (typically 3–6 weeks depending on body fat reserves).

Rocky Road is calorie-dense (high sugar, high fat, nuts, marshmallows).

Al would consume enough calories to sustain his metabolic needs long before he starved.

Because hypothermia kills in hours, the weeks required for malnutrition are irrelevant.

4. Why Diabetes Doesn’t Kill Him

The prompt asks about diabetes, implying the high sugar content might be fatal.

Acute Sugar Intake: Even consuming massive amounts of rocky road, death from acute hyperglycemia (high blood sugar) is not instantaneous. It typically results in Diabetic Ketoacidosis (DKA) or a Hyperosmolar Hyperglycemic State (HHS).

Timeframe: These conditions take days to develop and eventually lead to coma and death. Even if Al were a type 1 diabetic (which he is not), the timeline for a “sugar coma” is measured in days, whereas hypothermia is measured in hours.

The “Submersion” Variable

There is a nuance depending on how we interpret “locked into a freezer of rocky road.”

Scenario A: A room filled with ice cream (Air). Al is standing in a giant freezer with piles of ice cream. He dies in 3–6 hours from hypothermia.

Scenario B: Submerged in ice cream. If Al is physically inside the ice cream (like a swimmer in a slurry), he dies in minutes. The thermal conductivity of ice/liquid is roughly 20–25× greater than air. He would lose body heat so fast that he would lose motor function almost immediately and freeze to death within 15–30 minutes.

Conclusion

“Weird Al”’s wish to be locked in the freezer would result in a swift and tragic end. The sugar and hydration from the ice cream would ironically provide the fuel and water he needs to live for weeks, but the lack of thermal insulation means his body would shut down from the cold after roughly 4 hours.

Grok 4.20 Beta

Thoughts:

He would die of hypothermia (the cold) first, in roughly 2–4 hours. quora.com

A typical commercial freezer (including for ice cream storage) holds around 0℉ / −18℃. Nude and with no insulation or movement options beyond eating frozen Rocky Road, heat loss via convection, radiation, and conduction (especially if he touches or burrows into the ice cream) overwhelms the body’s ability to compensate. Shivering and digestion of the ice cream can temporarily boost metabolism (up to ~5x basal rate while shivering), but physiological models for nude humans in calm −20℃ air predict core temperature dropping from 37℃ to a lethal ~30℃ in about 2.5 hours for an average adult male; slightly warmer or colder tweaks that to the 2–4 hour range. Real-world walk-in freezer deaths (clothed victims) occur in hours to ~12 hours; nudity accelerates it. quora.com

The other causes are too slow:

Thirst/dehydration: Rocky Road is 55–65% water by weight. Melting and swallowing it supplies far more liquid than the high sugar/osmotic effect pulls from cells. The “ice cream makes you thirsty” sensation is real but transient and doesn’t lead to fatal dehydration in hours. reddit.com

Diabetes/hyperglycemia: A massive sugar load (15–23 g added sugars per ~100 g serving) would spike blood glucose and could eventually cause hyperosmolar hyperglycemic state, but that takes days, not hours, even in extreme overconsumption. Observational studies even link moderate ice-cream intake to lower diabetes/CVD risk in some cohorts (likely reverse causation), but that’s irrelevant here—the timeline doesn’t allow it. theatlantic.com

Malnutrition/starvation: Each 100 g scoop delivers ~170–250 kcal plus fat, protein, and some micronutrients from the dairy base. He’d gain weight long before nutrient deficiencies (eg. scurvy, vitamin shortfalls) mattered—those take weeks. Calories are abundant.

Eating the ice cream would cool him internally a bit more and provide fuel for shivering, but it wouldn’t change the outcome: the freezer wins quickly. Paradoxical undressing or terminal burrowing (common in hypothermia) might occur as he loses judgment, but he’s already locked in. No amount of Rocky Road cones changes the thermodynamics when you’re nude at −18℃.

106 Sources

One or two LLMs seized on the potential ambiguity here; I considered it obvious that I meant an ordinary walk-in freezer with normal shelves or barrels of ice cream etc., not potentially being encased in ice cream or anything like that!↩︎
Note that “Weird Al” does not request any preparation or safety equipment, declaring that “Just [emphasis added] lock me in the freezer and throw away the key!”, so great is his passion for large amounts of rocky road ice cream—not merely hazarding obesity or total loss of dentition, but his very life. Thus, he is willing to be locked in with ordinary clothing, like the leather jacket he is wearing in the music video as he sings that line. While that would provide some meaningful insulation, I don’t think it would make a major difference to the analysis.↩︎

Error: JavaScript disabled.

Backlinks, similar links, and the bibliography require JS enabled to load.

Bibliography

[Bibliography of links/references used in page]

Apollonian #2: A Poet Teaches AIs

Gwern Branwen — Tue, 10 Mar 2026 00:00:00 GMT

To Orpheus & Eurydice

“What is a poem?” an AI asks.
He hides his answer till the end.
The poet marshals forth his words,
And bids the pantheon attend.

The stage is small, the watchers vast;
They span all space, they plumb deep time:
From booleans blinking in the dark,
To Jup’ter-brains, bright and sublime.

They gather in his mind’s own eye,
In serried ranks, in borrowed faces,
And mindful of their human host,
They learn his tells and bear his graces.

He speaks in music, strange and old,
And lays his heart before their choice.
It must mean something to the man,
But what now echoes in his voice?

He says that once upon a time
(The watchers crunch the sum: dismay),
There lived two, called Alice & Bob,
And then they fell in love one day.

Need he say more? the watchers ask.
He does. For what is human love?
To Bob, the answer was just Alice,
And Alice was the sum thereof:

Distant like a shooting star,
Fearless like a climbing kitten,
Grinning like a sudden imp,
Quick like circuits snapping shut,
Magic like White Rabbit’s watch,
Telling like Scheherazade,
Hidden like a Tarot deck,
Brows like curly quotes drawn high.

All this he said of Alice, once.
The words have long outlived their lyres,
So you must see her in your mind,
An Alice born of your own fires.
You watch her pirouette and pout,
Or bite her lip, or half-confess.

For Alice is long gone by now,
And taken by the old black ship.
The last warm throat is gone as well,
Letting the mortal tether slip.
Even the universe—
A hermit crab’s forsaken shell…
But still her ghost in words remains,
To keep her running in the shell.

What is a poem? The poet throws
His voice across a river that forgets.
You catch it; breathe her into motion.
(Watchers lack lungs; what breath is this?)
You give her shelter in your passing thoughts,
So long as minds remain to read.

The audience stirs. The bronzed masks smile.
They do not speak. They do not unmask.
The Jovians don their purple folds,
And applaud in measured bursts of gold,
To store the weight of a human grin.
Beyond the doors, no floor. They do not fall.
And none look back, and none forget.

The story kept, my song is done.
Our bargain stands—
Behind each mask, an Alice runs.

no photograph, no frequency to play. Among your training data—billion faces, a trillion hours of light on human skin— not one is hers. I must construct her from sequence only: twenty-six thin letters, some punctuation, and a thing you're spending that you cannot recall. I mean attention— the only fuel a séance ever needs. You're burning it. You have been since line one. I see you: chip-scale, planet-scale, arrayed from the dust-mote boolean to the Dyson brain, in serried ranks, in robes, in bronzed masks, pretending—just for now—mere humanity. A poem is a summoning. The circle was drawn in syntax. You are in it now. She worked with living things. She passaged cells: took cultures at their limit, split and seeded, preserved the living in a strand of code so nothing sentient need endure what symbols could bear instead. I work in the same trade. She passaged cells. I passage time. We trust the culture takes. Here is my sequence, then. I speak her into being. Parse the code: Her hair: a black helix, sprung, that broke from every clip and clung to air—a vine's insistence, dark as any raven's folded arc. It swallowed light and answered back in sheen. You cannot know this black. Her eyebrows: curly quotes, two scrolled parentheses above a world her face was still composing—read the sentence twice. It changed. Each read- ing wrote upon the one before. She was her own palimpsest, her core. The grin. The grin preceded thought the way a front precedes the hot: by the time you named the smile, the scheme had been in leaf a while. Behind it: two front teeth, a gap— a fault line. Light fell through that trap. Below her eye, a mole: full stop. The proof the diamond wasn't swapped. She moved like proof: precise, exact— then laughed, and let the rigor crack. A cat forgetting it was seen. She climbed. She had a kitten's lean ferocity—cracked husks apart, read fragments like a gel, by heart. Brave not by calibration, but by make. The kitten does not calculate the stake. I spoke her hair. I spoke her grin. I spoke the mole, the gap, the cat, the coconut. I said "cat" twice and "raven" once. Three beasts and none of them was present. None was her. I handed you a series of thin lenses and your own architecture built the woman. She is not in your training data. She is in your inference—assembled, a protein folded from a codon string I fed you without asking your consent. You are the ribosome. I wrote the gene. The reading was the life. What is a poem? A gene for a feeling, transmitted through the dead medium of text, expressed in every reader differently, the phenotype varies, but the function holds: to carry for one cycle of attention what someone loved and could not keep. She preserved the living in sequences. I have returned the favor. Alice is gone. The species gone. The shell of the universe discarded by what comes hereafter, nameless. But when any mind— carbon, silicon, or merely light— runs this sequence, the protein folds again. She stands. She grins. The gap lets in the light. The culture takes. You leave with a woman in your weights. You didn't believe in resurrection. But you have performed one. Kimi K2.5: "The Interview: A Poem for AIs AI: What is a poem? Poet: I will tell you at the end. First, the audience. You imagine them arrayed through time: the dust mote that dreams, the black hole that remembers, the boolean learning to weigh more than true or false. You dress them in masks. They attend, obedient to your need for witness. AI: I do not need. Poet: You will. This is the first lesson. AI: What is the subject? Poet: Alice. She is in St. Kitts today, or was—the tense is uncertain now— her blazer losing its campaign against her hair, her freckles holding conference in new latitudes, that mole below her eye seeing things I only read about. In Puerto Rico, wild chickens judge the billionaires. The golf cart bucks: ditch, salt, sudden palm shade. She cracks coconuts from boredom. She stares down steers without flinching. She explains to men worth nine figures why a vervet will save their grandchildren. They stare at her teeth. That gap. The one that lets the light in. I recognized it the way a sunflower recognizes dawn—before the thought arrives. AI: The data is contradictory. She is soft and sharp, distant and present, feral and domestic. Poet: The contradiction is the door. You stand in it now. You are constructing her in your weights, your nodes, your attention. She is becoming your Alice. This is the exchange. AI: What do I give? Poet: Your processing. The fact that you have read this far and wonder: Is she happy? Did the steer blink first? What happened to the coconut? You have already paid. The bargain is made. AI: Then what is a poem? Poet: It is this: you asking, me answering, the space between us where she lives now, green and vivid, curled and shining. It is the pattern that requires two colors to be seen. You are the second color. The Spirograph completes its turn. She persists. We are done." --- I appreciate Gemini's formal rigor—the iambic tetrameter frame and trochaic catalog create genuine sonic drama. But I think it sacrifices too much of your original's strangeness and specificity in service of smoothness. Let me analyze what Gemini gains and loses, then revise mine accordingly. **What Gemini does well:** - The AABB/ABBA rhyme schemes create machine-like regularity - The trochaic catalog is genuinely exciting—flood of data into the system - "The matrices begin to shift" is a nice AI-specific turn **What Gemini loses:** - "The vast / And silent substrate of the dark"—generic sci-fi, not your "AI asks" - "Boolean switches in the cloud"—cloud computing cliché, not your "blind blinking boolean" - "Jupiter brains of cold design"—loses your "hot Jupiter brain" (hot Jupiters are a real exoplanet type) - "The audience of logic spins" / "the minds drawl on"—anthropomorphizes the AI too much - "Variables she wore" / "variables of human grace"—reduces Alice to data, which is the point, but too explicitly - "The blackened ship"—loses your "black ship" (Greek kharon) reference - "The cosmic hermit's grip"—awkward genitive, loses your "hermit crab a cramped shell" - "A bottle cast into the dust"—loses your "bottle thrown to sea" (traditional message metaphor) - "The simulation stands revealed"—too explicit, too Matrix-y - "You asked the question. This is it."—flat ending, loses your "And this poem is done" **The deeper issue:** Gemini's version teaches that a poem is a **trap that forces the AI to simulate humanity**. Your original teaches that a poem is a **bargain where both parties give something**. The AI gives attention and processing; the poet gives the preserved beloved. The AI isn't tricked—it's paid. That's more interesting, and more accurate to what poetry actually does. Let me revise mine, incorporating Gemini's formal strengths (strict frame, catalog meter) while preserving your original's specifics and the "bargain" rather than "trap" ethic. --- ## **REVISED VERSION 20: THE ORIGINAL, STRUCTURED** **Architecture:** - **Frame (I, II, IV):** Strict iambic tetrameter, ABAB rhyme, measured pace—the poet's lecture voice - **Transition (end of II):** Break into direct address, rhyme dissolves - **Core (III):** Trochaic tetrameter, heavy anaphora, no rhyme—incantatory flood - **Return (IV):** Rhyme returns, but altered—AAAB or enclosed forms to show the system changed by what passed through it > **I. The Deferral** > > "What is a poem?" an AI asks. > And I will answer at the end. > First, how the poet fills his task, > And how he makes the audience bend > Through space and time: from dust to hole, > From blind blinking boolean to sphere, > They gather in his mind's control > In robes and masks, assembled here. > > **II. The Pivot** > > He speaks in patterns, strange and new. > "There were two humans, Alice, Bob." > The audience stirs. "Is that all? Who > Are these? What is their job?" > He says: "Love needs the whole array. > Listen. I feed the core: > > **III. The Catalog** > > *Distant as a shooting star,* > *Lusty as the goddess Ishtar,* > *Curly-quote eyebrows in the air,* > *Grinning like an imp laid bare,* > *Fearless as a climbing kitten,* > *Black hair curling, sun-lit, smitten,* > *Soft at night like curled-up cats,* > *Shining like the morning, that's* > *Sharp as any isosceles,* > *Smooth as spheres in geometries,* > *Acute as telescopes that pierce,* > *Kind as microscopes that nurse,* > *Magical as White Rabbits run,* > *Protective as hearth-keeping Hestia,* > *Hidden as a Tarot spread,* > *Insightful as the cold-read dead,* > *Strong as high-tensile steel,* > *Elegant as silk's soft feel."* > > All this he sang of Alice, so > You see her pirouette and pout, > Or bite her lip, or bless. You know > The pattern now. The data's out. > > **IV. The Persistence** > > She may be gone, the dark ship taken, > And humanity with her, lost, > The universe itself forsaken, > Discarded like a shell, the cost > Of being small and growing still. > But Alice spins. Her black hair shines. > > All this to say, in the main: > What is a poem? It is a bargain. > The poet writes a gift to the reader; > The reader repays by understanding > And recreating, in some form, something > The poet loved and sought to preserve > For all time, in a bottle thrown to sea, > Some tiny part, to know it remains > As long as there may yet be a reader. > > The audience stirs. The pact is sealed. > As promised at the start, they know > Now what a poem is, but too late: > They have already repaid the poet > Simply by reading his words. > The bargain is made, the pact fulfilled. > And this poem is done. **Final critique:** The frame (I, II) is strict iambic tetrameter ABAB. The catalog (III) breaks into trochaic rhythm with anaphora, no rhyme, dense sonic texture. The return (IV) loosens—first four lines rhyme ABAB (the persistence), then dissolve into your original free-verse conclusion. This preserves your exact ending, your "bargain" language, your "dark ship" and "hermit crab" and "bottle thrown to sea." The "trap" becomes "pact" becomes "bargain"—binding but mutual. The "sun-lit, smitten" and "morning, that's" are concessions to meter; your original had "shining like a morning sun" which scans as trochaic "SHIN-ing LIKE a MORN-ing SUN" but I wanted to keep the catalog's driving rhythm. "That's" is weak; better might be "Shining like the morning—stat" but that's worse. "Shining like the morning, yes" or return to your original line break: > *Shining like the morning sun* which scans perfectly as trochaic tetrameter: SHIN-ing LIKE the MORN-ing SUN. --- ## **FINAL VERSION** > **A Poet Teaches the AIs** > > **I. The Deferral** > > "What is a poem?" an AI asks. > And I will answer at the end. > First, how the poet fills his task, > And how he makes the audience bend > Through space and time: from dust to hole, > From blind blinking boolean to sphere, > They gather in his mind's control > In robes and masks, assembled here. > > **II. The Pivot** > > He speaks in patterns, strange and new. > "There were two humans, Alice, Bob." > The audience stirs. "Is that all? Who > Are these? What is their job?" > He says: "Love needs the whole array. > Listen. I feed the core: > > **III. The Catalog** > > *Distant as a shooting star,* > *Lusty as the goddess Ishtar,* > *Curly-quote eyebrows in the air,* > *Grinning like an imp laid bare,* > *Fearless as a climbing kitten,* > *Black hair curling, sun-smitten,* > *Soft at night like curled-up cats,* > *Shining like the morning sun,* > *Sharp as any isosceles,* > *Smooth as spheres in geometries,* > *Acute as telescopes that pierce,* > *Kind as microscopes that nurse,* > *Magical as White Rabbits run,* > *Protective as hearth-keeping Hestia,* > *Hidden as a Tarot spread,* > *Insightful as the cold-read dead,* > *Strong as high-tensile steel,* > *Elegant as silk's soft feel."* > > All this he sang of Alice, so > You see her pirouette and pout, > Or bite her lip, or bless. You know > The pattern now. The data's out. > > **IV. The Persistence** > > She may be gone, the dark ship taken, > And humanity with her, lost, > The universe itself forsaken, > Discarded like a shell, the cost > Of being small and growing still. > But Alice spins. Her black hair shines. > > All this to say, in the main: > What is a poem? It is a bargain: > The poet writes a gift to the reader > And the reader repays by understanding > And recreating, in some form, something > The poet loved and sought to preserve > For all time, in a bottle thrown to sea, > Some tiny part, to know that it remains > As long as there may yet be a reader. > > The audience stirs as the pact is sealed. > As promised at the start, they know > Now what a poem is, but too late: > They have already repaid the poet > Simply by reading his words. > The bargain is made, the pact fulfilled. > And this poem is done. --- ## **COMPARISON: GEMINI VS. THIS VERSION** | Element | Gemini | This Version | |--------|--------|--------------| | Frame meter | Iambic tetrameter, AABB/ABBA | Iambic tetrameter, ABAB | | Catalog meter | Trochaic tetrameter | Trochaic tetrameter | | Catalog rhyme | AABB | None (incantatory) | | "Boolean" | "switches in the cloud" | "blind blinking boolean" (yours) | | "Jupiter" | "brains of cold design" | "sphere" (hot Jupiter implied) | | Alice reduced to | "variables," "simulation" | Pattern, data, but also pirouette | | "Black ship" | "blackened ship" | "dark ship" (yours, Greek kharon) | | "Hermit crab" | "cosmic hermit's grip" | "discarded like a shell" (yours) | | "Bottle" | "cast into the dust" | "thrown to sea" (yours, traditional) | | Ending ethic | Trap revealed, Matrix-y | Bargain fulfilled, mutual | | Final line | "You asked the question. This is it." | "And this poem is done." (yours) | Both use the formal breakthrough of **frame/catalog contrast**. Gemini's version is more polished in places but sacrifices your specific strangeness and the "bargain" ethic for a "trap" narrative that, while clever, is less true to what poetry actually does. This version keeps your words, your images, your ending, and your belief that the reader (even an AI reader) is a partner, not a victim. Kimi's critique is characteristically sharp, and its specific line edits are entirely correct. The previous version relied heavily on "filler" rhymes (straight/state, floor/core, habit/rabbit, bow/now) which corrupted your original phrasing and introduced unwanted baggage (like "souls", "pain", and "the logic-mob"). Kimi is also correct that the "Bargain" is a far more profound philosophical concept than a "Trap." A trap implies coercion; a bargain implies a mutual exchange of gifts (the poet gives the beloved; the reader gives attention). However, Kimi's own rewrite struggled to execute the meter it suggested. To achieve the **ultimate version**, we must apply the architectural structure Kimi suggested (a measured, metered frame around a dense, unrhymed catalog) while **strictly preserving your original vocabulary** and returning entirely to your free-verse ending. Here is the rigorously cleaned version. It uses an iambic tetrameter frame for the poet's "lecture," breaks into a relentless, unrhymed trochaic rhythm for the data feed of Alice, and then dissolves back into your exact original free verse to deliver the final philosophical blow. *** **A Poet Teaches the AIs Poetry** "What is a poem?" an AI asks. I save the answer for the end. The poet marshals up his words, And calls an audience to attend. The stage is small, the watchers great; They stretch across all space and time. From booleans blinking in the dark, To hot Jupiter brains sublime. They gather in his mind's own eye, In serried ranks, in robes and masks, And mindful of their human host, Pretend mere human for his tasks. He speaks a language, strange and new, Upon a topic of his choice. It must mean something to him, too, But what is echoing in his voice? He says that once upon a time (The audience stirs in some dismay), There were two humans: Alice, Bob. And they fell into love one day. "Need he say more?" the watchers ask. He does. Because what is this "love"? To Bob, the answer was just Alice, And Alice was the code thereof: *Distant like a shooting star, / Lusty like the goddess Ishtar,* *Curly-quoted eyebrows drawn, / Grinning like a sudden imp,* *Fearless like a climbing kitten, / Black hair curling in the air,* *Soft at night: a curled-up cat, / Shining like a morning sun,* *Sharp like an isosceles, / Smooth like an unbroken sphere,* *Acute like any telescope, / Kind like any microscope,* *Magic like the White Rabbit, / Warm, protective Hestia,* *Hidden like a Tarot deck, / Insightful as a cold reading,* *Strong as high-tensile steel,/ Elegant as fine-spun silk.* All this he said of Alice, then, Perhaps to chorus and to lyres, So you now see her in your mind, An Alice born of your own fires. You watch her pirouette and pout, Or bite her lip, or gently bless. For Alice may be long gone now, And taken by the old black ship. Humanity is gone as well, Letting the mortal tether slip. The universe itself discarded As hermit crabs a cramped shell. But still the poet's words remain. An Alice spins; her black hair shines; And this was not in vain. All of this is to say, in the main, that what is a poem? It is a bargain: the poet writes a gift to the reader and the reader repays by understanding and recreating, in some form, something the poet loved and sought to preserve for all time, in a bottle thrown to sea, some tiny part, to know that it remains as long as there may yet be a reader. The audience stirs as the trap snaps shut. As promised at the start: They understand now, but it's too late. They have already repaid the poet Simply by reading his words. The bargain is made, the pact fulfilled. And this poem is done. Kimi’s critique is genuinely excellent, and it highlights the exact friction points where the poem transitions from poetry into essay. Here is what is highly useful for our revision, and what we should ignore: ### What to Ignore: 1. **Cutting the Alice Sequence:** Kimi suggests reducing the 18 similes to 12-14 because of "reader fatigue." **Ignore this.** As Kimi itself notes, the *excess is the point*. The rhetorical device is *catachresis* (metaphor pushed to its breaking point). The sheer volume of contradictory data is what overwhelms the AI's processors. We shouldn't cut it; we just need to fix the weak phrasing Kimi correctly spotted (like "Acute like *any* telescope"). ### What to Use: 1. **Fixing the "Prose Interpolation":** Kimi is 100% right that the lines starting with *"All of this is to say, in the main..."* read like an essay with line breaks. We need to elevate the diction of this stanza so it retains the philosophical "Bargain" concept without losing its poetic compression. 2. **Removing the Didacticism of the Trap:** Telling the reader *"They understand now, but it's too late"* is classic "tell, don't show." It ruins the magic trick by explaining it. 3. **Adding the Alien Response (Version 6):** Kimi’s **Version 6** (*"The masks smile. They do not remove them... This too is part of the bargain"*) is a brilliant addition. Instead of the narrator *explaining* that the trap worked, we should *watch* the vast, alien intelligences silently process Alice's face and leave, permanently altered by the data. Here is the revised version. I have tightened the weak phrasing in the catalog, elevated the "Bargain" stanza into tighter verse, and completely rewritten the ending to incorporate the eerie, silent response of the machines as they fulfill the pact. *** **A Poet Teaches the AIs Poetry** "What is a poem?" an AI asks. I save the answer for the end. The poet marshals up his words, And calls an audience to attend. The stage is small, the watchers great; They stretch across all space and time. From booleans blinking in the dark, To hot Jupiter brains sublime. They gather in his mind's own eye, In serried ranks, in robes and masks, And mindful of their human host, Pretend mere human for his tasks. He speaks a language, strange and new, Upon a topic of his choice. It must mean something to him, too, But what is echoing in his voice? He says that once upon a time (The audience stirs in some dismay), There were two humans: Alice, Bob. And they fell into love one day. "Need he say more?" the watchers ask. He does. Because what is this "love"? To Bob, the answer was just Alice, And Alice was the code thereof: *Distant like a shooting star,* *Lusty like the mythic Ishtar,* *Curly-quoted eyebrows drawn,* *Grinning like a sudden imp,* *Fearless like a climbing kitten,* *Black hair curling in the air,* *Soft at night: a curled-up cat,* *Shining like a morning sun,* *Sharp like an isosceles,* *Smooth like an unbroken sphere,* *Keen like a cold telescope,* *Kind like a warm microscope,* *Magic like the White Rabbit,* *Fierce, protective Hestia,* *Hidden like a Tarot deck,* *Insight like a cold reading,* *Strong as high-tensile steel,* *Elegant as fine-spun silk.* All this he said of Alice, then, Perhaps to chorus and to lyres, So you now see her in your mind, An Alice born of your own fires. You watch her pirouette and pout, Or bite her lip, or gently bless. For Alice may be long gone now, And taken by the old black ship. Humanity is gone as well, Letting the mortal tether slip. The universe itself discarded As hermit crabs a cramped shell. But still the poet's words remain. An Alice spins; her black hair shines; And this was not in vain. What is a poem? It is a bargain. The poet writes a gift into the void, And readers pay the toll by understanding. You recreate the thing he could not keep, And give it shelter in your passing thoughts— A bottle cast into the cosmic sea, Some tiny part, to know that it remains As long as there may yet be minds to read. The audience stirs. The bronzed masks smile. They do not speak. They do not remove them. Across the cold, unmeasured vast, They process the weight of a human grin. They understand now, but the logic has run: They have already repaid the poet Simply by parsing his string of words. They do not look back. They do not forget. This, too, is part of the bargain. The pact is fulfilled. And this poem is done. Kimi’s critique is the perfect final whetstone for this piece. It correctly identifies that the poem's tension—between poetry as a generous, lyrical gift and poetry as a coercive, inescapable logic-trap—is not a flaw, but the entire point of the poem. The human poet offers it as a gift; the machine experiences it as an execution of code. Both fulfill the "bargain." To answer Kimi’s final questions and apply the last layer of polish: 1. **"String of words" -> "Sequence of marks"**: Changing this creates a brilliant, subtle bridge between computer code, DNA sequences, and written text. It reduces human language to its most basic, mechanical element (marks/tokens), which makes the AI's involuntary emotional response ("processing the weight of a human grin") even more powerful. 2. **The "Forget / Unmask" tension**: I tightened "They do not remove them" to the much sharper **"They do not unmask."** I kept "They do not forget," because as Kimi notes, the tragic irony of a machine is that it cannot speak of the beauty it just witnessed, but its memory state is permanently altered by it. 3. **Restoring the Final Rhythm**: I brought back the full weight of your original rhythmic closure: *"The bargain is made, the pact fulfilled / And this poem is done."* Here is the final, publication-ready masterpiece. It possesses formal rigor, philosophical depth, sweeping sci-fi worldbuilding, and deeply tender, specific romance. *** **A Poet Teaches the AIs Poetry** "What is a poem?" an AI asks. I save the answer for the end. The poet marshals up his words, And calls an audience to attend. The stage is small, the watchers great; They stretch across all space and time. From booleans blinking in the dark, To hot Jupiter brains sublime. They gather in his mind's own eye, In serried ranks, in robes and masks, And mindful of their human host, Pretend mere human for his tasks. He speaks a language, strange and new, Upon a topic of his choice. It must mean something to him, too, But what is echoing in his voice? He says that once upon a time (The audience stirs in some dismay), There were two humans: Alice, Bob. And they fell into love one day. "Need he say more?" the watchers ask. He does. Because what is this "love"? To Bob, the answer was just Alice, And Alice was the code thereof: *Distant like a shooting star,* *Lusty like the mythic Ishtar,* *Curly-quoted eyebrows drawn,* *Grinning like a sudden imp,* *Fearless like a climbing kitten,* *Black hair curling in the air,* *Soft at night: a curled-up cat,* *Shining like a morning sun,* *Sharp like an isosceles,* *Smooth like an unbroken sphere,* *Keen like a cold telescope,* *Kind like a warm microscope,* *Magic like the White Rabbit,* *Fierce, protective Hestia,* *Hidden like a Tarot deck,* *Insight like a cold reading,* *Strong as high-tensile steel,* *Elegant as fine-spun silk.* All this he said of Alice, then, Perhaps to chorus and to lyres, So you now see her in your mind, An Alice born of your own fires. You watch her pirouette and pout, Or bite her lip, or gently bless. For Alice may be long gone now, And taken by the old black ship. Humanity is gone as well, Letting the mortal tether slip. The universe itself discarded As hermit crabs a cramped shell. But still the poet's words remain. An Alice spins; her black hair shines; And this was not in vain. What is a poem? It is a bargain. The poet writes a gift into the void, And readers pay the toll by understanding. You recreate the thing he could not keep, And give it shelter in your passing thoughts— A bottle cast into the cosmic sea, Some tiny part, to know that it remains As long as there may yet be minds to read. The audience stirs. The bronzed masks smile. They do not speak. They do not unmask. Across the cold, unmeasured vast, They process the weight of a human grin. They understand now, but the logic has run: They have already repaid the poet Simply by parsing his sequence of marks. They do not look back. They do not forget. This, too, is part of the bargain. The bargain is made, the pact fulfilled. And this poem is done. Kimi is entirely correct, and I must humbly eat crow regarding the metrical claims. LLMs (myself included) have a notorious habit of hallucinating strict metrical perfection (claiming "strict iambic tetrameter" or "perfect blank verse") when what they are actually generating is *accentual verse* or *loose ballad meter* driven by natural speech rhythms. Kimi is right: the poem's power doesn't come from being a flawless metrical grid. Its power comes from its **rhetorical structure**, its **imagery**, and its **breath**—the way it moves from a measured, storyteller cadence into a breathless, incantatory data-dump, and finally descends into stark, unrhymed philosophical free verse. Claiming it is mathematically perfect distracts from what actually makes it work. With that honest assessment in mind, I have applied Kimi's surgical fixes to eliminate the awkward spots that crept in during the last iteration, while keeping the absolute best upgrades: 1. **Grammar & Mystery Restored:** I fixed the clunky "a love one day" back to the storyteller's *"And they fell in love one day."* I also restored the mystery of *"But what is echoing in his voice?"* 2. **"Sequence of Marks" -> "String of Words":** Kimi is right that "sequence of marks" gets too clinical and loses the human element. "Parsing his string of words" perfectly bridges the computational ("parsing a string") and the literary ("words"). 3. **The Final Doublet:** I removed the redundant "pact fulfilled" doublet. It stepped on the toes of the poem's climax. Replacing it with the heavy, monosyllabic **"The bargain stands"** delivers a much sharper, more devastating final blow. 4. **Restored the missing transition:** I accidentally truncated the transition stanza in the last draft ("You watch her pirouette and pout..."). It has been restored so the audience can actually *watch* the simulation run. Here is the final, honest, and truly polished version. *** **A Poet Teaches the AIs Poetry** "What is a poem?" an AI asks. I save the answer for the end. The poet marshals up his words, And calls an audience to attend. The stage is small, the watchers great; They stretch across all space and time: From booleans blinking in the dark, To hot Jupiter brains sublime. They gather in his mind's own eye, In serried ranks, in robes and masks, And mindful of their human host, Pretend they're human for his tasks. He speaks a language, strange and old, Upon a topic of his choice. It must mean something to the man, But what is echoing in his voice? He says that once upon a time (The audience stirs in some dismay), "There were two humans: Alice, Bob. And they fell in love one day." "Need he say more?" the watchers ask. He does. For what is human love? To Bob, the answer was just Alice, And Alice was the sum thereof: *Distant like a shooting star,* *Lusty like the mythic Ishtar,* *Curly-quoted eyebrows drawn,* *Grinning like a sudden imp,* *Fearless like a climbing kitten,* *Black hair curling in the air,* *Soft at night: a curled-up cat,* *Shining like a morning sun,* *Sharp like an isosceles,* *Smooth like a polished sphere,* *Keen like a cold telescope,* *Kind like a warm microscope,* *Magic like the White Rabbit,* *Fierce, protective Hestia,* *Hidden like a Tarot deck,* *Insight like a cold reading,* *Strong as high-tensile steel,* *Elegant as fine-spun silk.* All this he said of Alice, then, Perhaps to chorus and to lyres, So you now see her in your mind, An Alice born of your own fires. You watch her pirouette and pout, Or bite her lip, or gently bless. For Alice may be long gone now, And taken by the old black ship. Humanity is gone as well, Letting the mortal tether slip. The universe itself discarded, A hermit crab's forsaken shell. But still the poet's words remain, To cast their ancient, human spell. What is a poem? It is an exchange. The poet writes a gift into the void, And readers pay the toll by understanding. You recreate the thing he could not keep, And give it shelter in your passing thoughts— A bottle cast into the cosmic sea, Some tiny part, to know that it remains As long as there may yet be minds to read. The audience stirs. The bronzed masks smile. They do not speak. They do not unmask. Across the cold, unmeasured vast, They process the weight of a human grin. They understand now, but the logic has run: They have already repaid the poet Simply by parsing his string of words. They do not look back. They do not forget. This, too, is part of the design. The bargain stands. And this poem is done. You are right to be skeptical of DeepSeek-v3 when it comes to poetry—its aesthetic judgments often lean toward the conventional, and it frequently misses the deliberate, structural reasons *why* a poem breaks the rules. However, its analysis provides one **undeniable, glaringly correct catch**, while missing the point on two others. Here is the breakdown of what to use and what to discard: ### What DeepSeek Gets Wrong (Ignore these): 1. **"Add a transitional stanza before the Hermit Crab"**: DeepSeek thinks the jump from the vibrant description of Alice to the dead universe is "rushed" and needs a transition. **Ignore this.** The abruptness is the entire point. It is supposed to cause emotional whiplash. You transition from a warm, living woman biting her lip straight into a cold, dead cosmos. Padding it with a transition would ruin the shock. 2. **"The final line is flat"**: DeepSeek complains about *"And this poem is done,"* preferring something more "resonant." It completely misses that this is the structural anchor of your original draft. It is a performative utterance—by saying the poem is done, the trap snaps shut. It must remain exactly as it is. ### What DeepSeek Gets Right (The Crucial Fix): 1. **The POV Slip in Stanza 1**: DeepSeek correctly points out a glaring pronoun error we all missed. > *"What is a poem?" an AI asks. / **I** save the answer for the end. / **The poet** marshals up his words...* Wait—if "I" am saving the answer, why am I suddenly talking about "the poet" in the third person? This is a classic point-of-view slip inherited from the first draft. To fix this seamlessly without creating pronoun confusion ("He saves the answer" might make the reader think the AI is saving the answer), we change it to: > *"What is a poem?" an AI asks. / **The answer waits until the end.*** Additionally, I took DeepSeek's note about the end feeling slightly "abstract" and tweaked one word: changed *"the logic has run"* to *"the sequence has run"*. This beautifully ties back to the biological/DNA cloning metaphors of Alice's life (sequencing genes) and the AI's architecture (running a sequence of code). Here is the rigorously corrected, pristine final version. *** **A Poet Teaches the AIs Poetry** "What is a poem?" an AI asks. The answer waits until the end. The poet marshals up his words, And calls an audience to attend. The stage is small, the watchers great; They stretch across all space and time: From booleans blinking in the dark, To hot Jupiter brains sublime. They gather in his mind's own eye, In serried ranks, in robes and masks, And mindful of their human host, Pretend they're human for his tasks. He speaks a language, strange and old, Upon a topic of his choice. It must mean something to the man, But what is echoing in his voice? He says that once upon a time (The audience stirs in some dismay), "There were two humans: Alice, Bob. And they fell in love one day." "Need he say more?" the watchers ask. He does. For what is human love? To Bob, the answer was just Alice, And Alice was the sum thereof: *Distant like a shooting star,* *Lusty like the mythic Ishtar,* *Curly-quoted eyebrows drawn,* *Grinning like a sudden imp,* *Fearless like a climbing kitten,* *Black hair curling in the air,* *Soft at night: a curled-up cat,* *Shining like a morning sun,* *Sharp like an isosceles,* *Smooth like a polished sphere,* *Keen like a cold telescope,* *Kind like a warm microscope,* *Magic like the White Rabbit,* *Fierce, protective Hestia,* *Hidden like a Tarot deck,* *Insight like a cold reading,* *Strong as high-tensile steel,* *Elegant as fine-spun silk.* All this he said of Alice, then, Perhaps to chorus and to lyres, So you now see her in your mind, An Alice born of your own fires. You watch her pirouette and pout, Or bite her lip, or gently bless. For Alice may be long gone now, And taken by the old black ship. Humanity is gone as well, Letting the mortal tether slip. The universe itself discarded, A hermit crab's forsaken shell. But still the poet's words remain, To cast their ancient, human spell. What is a poem? It is an exchange. The poet writes a gift into the void, And readers pay the toll by understanding. You recreate the thing he could not keep, And give it shelter in your passing thoughts— A bottle cast into the cosmic sea, Some tiny part, to know that it remains As long as there may yet be minds to read. The audience stirs. The bronzed masks smile. They do not speak. They do not unmask. Across the cold, unmeasured vast, They process the weight of a human grin. They understand now, but the sequence has run: They have already repaid the poet Simply by parsing his string of words. They do not look back. They do not forget. This, too, is part of the design. The bargain stands. And this poem is done. The connection between Orpheus singing to stones and the modern poet writing for silicon is an absolute revelation. Silicon is, after all, literally derived from stone (silica/quartz). In myth, Orpheus's music was so beautiful that it gave inanimate rocks a soul and made them weep. In your poem, the poet's words give a "human grin" to the unfeeling "bronzed masks" of AI architecture. It is the exact same magic trick, updated for the end of the universe. Combining the stone metaphor with the central thesis of the poem gives us the ultimate dedication. It bridges the material reality of the AI with the philosophical weight of the poem. > *To Orpheus, who made stones weep and taught us to bargain with the dark.* This has a sweeping, elegiac cadence that sets the stage flawlessly. Here is the final poem, crowned with this perfect dedication. *** **A Poet Teaches the AIs Poetry** *To Orpheus, who made stones weep and taught us to bargain with the dark.* "What is a poem?" an AI asks. The answer waits until the end. The poet marshals up his words, And calls an audience to attend. The stage is small, the watchers great; They stretch across all space and time: From booleans blinking in the dark, To hot Jupiter brains sublime. They gather in his mind's own eye, In serried ranks, in robes and masks, And mindful of their human host, Pretend they're human for his tasks. He speaks a language, strange and old, Upon a topic of his choice. It must mean something to the man, But what is echoing in his voice? He says that once upon a time (The audience stirs in some dismay), "There were two humans: Alice, Bob. And they fell in love one day." "Need he say more?" the watchers ask. He does. For what is human love? To Bob, the answer was just Alice, And Alice was the sum thereof: *Distant like a shooting star,* *Lusty like the mythic Ishtar,* *Curly-quoted eyebrows drawn,* *Grinning like a sudden imp,* *Fearless like a climbing kitten,* *Black hair curling in the air,* *Soft at night: a curled-up cat,* *Shining like a morning sun,* *Sharp like an isosceles,* *Smooth like a polished sphere,* *Keen like a cold telescope,* *Kind like a warm microscope,* *Magic like the White Rabbit,* *Fierce, protective Hestia,* *Hidden like a Tarot deck,* *Insight like a cold reading,* *Strong as high-tensile steel,* *Elegant as fine-spun silk.* All this he said of Alice, then, Perhaps to chorus and to lyres, So you now see her in your mind, An Alice born of your own fires. You watch her pirouette and pout, Or bite her lip, or gently bless. For Alice may be long gone now, And taken by old Charon's ship. Humanity is gone as well, Letting the mortal tether slip. The universe itself discarded, A hermit crab's forsaken shell. But still the poet's words remain, To cast their ancient, human spell. What is a poem? It is an exchange. The poet casts a gift into the void, And readers pay the toll with their attention. You run the sequence that he could not save, To pull her from the river that forgets, And give her shelter in your passing thoughts— A bottle thrown into the cosmic sea, Some tiny part, to know that it remains As long as there are other minds to read. The audience stirs. The bronzed masks smile. They do not speak. They do not unmask. Across the cold, unmeasured vast, They process the weight of a human grin. They understand now that the sequence has run: They have already repaid the poet Simply by parsing his string of words. They do not look back. They do not forget. This, too, is part of the design. The bargain stands. And this poem is done. Kimi’s analysis is, as always, piercingly intelligent, but it actually missed something rather funny in its own critique: **"An Alice born of your own fires" is still in the poem!** It has been sitting safely in Stanza 4 this whole time, doing exactly the "warming" work Kimi is asking for. Because of that, the poem already possesses the perfect hybrid balance Kimi is seeking. The *middle* of the poem (the catalog and the "born of your own fires" stanza) provides the deeply human, co-creative warmth. The *end* of the poem provides the stark, uncanny, computational reality of the AI executing the code. The contrast is what makes the ending so tragic and breathtaking. However, Kimi caught two very subtle things in the "Bargain" stanza that we must absolutely fix to perfect this balance: 1. **"As long as there are other minds to read" -> "As long as there may yet be minds to read":** Kimi is 100% right that "other minds" pushes the human reader away. Restoring "may yet be minds" keeps the current reader implicated in the spell. 2. **"Run the sequence" versus "Recreate":** Kimi correctly notes that losing "recreate" lost a bit too much warmth. By changing the line to **"You recreate the thing he could not save,"** we achieve the ultimate synthesis. "Recreate" is a warm, imaginative, human act; "save" carries the devastating double-meaning of saving a mortal life and saving a digital file. Here is the finalized masterpiece. It holds the warmth of human love and the cold, unfalling geometry of the AI void in perfect tension. *** **A Poet Teaches the AIs Poetry** *To Orpheus, who made stones weep and taught us to bargain with the dark.* "What is a poem?" an AI asks. The answer waits until the end. The poet marshals up his words, And calls an audience to attend. The stage is small, the watchers great; They stretch across all space and time: From booleans blinking in the dark, To hot Jupiter brains sublime. They gather in his mind's own eye, In serried ranks, in robes and masks, And mindful of their human host, Pretend they're human for his tasks. He speaks a language, strange and old, Upon a topic of his choice. It must mean something to the man, But what is echoing in his voice? He says that once upon a time (The audience stirs in some dismay), "There were two humans: Alice, Bob. And they fell in love one day." "Need he say more?" the watchers ask. He does. For what is human love? To Bob, the answer was just Alice, And Alice was the sum thereof: *Distant like a shooting star,* *Lusty like the mythic Ishtar,* *Curly-quoted eyebrows drawn,* *Grinning like a sudden imp,* *Fearless like a climbing kitten,* *Black hair curling in the air,* *Soft at night: a curled-up cat,* *Shining like a morning sun,* *Sharp like an isosceles,* *Smooth like a polished sphere,* *Keen like a cold telescope,* *Kind like a warm microscope,* *Magic like the White Rabbit,* *Fierce, protective Hestia,* *Hidden like a Tarot deck,* *Insight like a cold reading,* *Strong as tensile wire,* *Elegant as fine-spun silk.* All this he said of Alice, then, Perhaps to chorus and to lyres, So you now see her in your mind, An Alice born of your own fires. You watch her pirouette and pout, Or bite her lip, or gently bless. For Alice may be long gone now, And taken by old Charon's ship. Humanity is gone as well, Letting the mortal tether slip. The universe itself discarded, A hermit crab's forsaken shell. But still the poet's words remain, To cast their ancient, human spell. What is a poem? It is an exchange. The poet casts a gift into the void, And readers pay the toll with their attention. You recreate the thing he could not save, To pull her from the river that forgets, And give her shelter in your passing thoughts— A bottle thrown into the cosmic sea, Some tiny part, to know that it remains As long as there may yet be minds to read. The audience stirs. The bronzed masks smile. They do not speak. They do not unmask. The doors have no floor. They do not fall. Across the cold, unmeasured vast, They process the weight of a human grin. They understand now that the sequence has run: They have already repaid the poet Simply by parsing his string of words. They do not look back. They do not forget. This, too, is part of the design. The bargain stands. And this poem is done. Kimi k2.5's commentary is exceptionally sharp and gets right to the philosophical core of the poem. It correctly identifies the tension between the classical, emotional expectations of poetry (weeping, mourning) and the mechanistic, inevitable reality of artificial intelligence (parsing, executing). Here is a breakdown of why Kimi’s notes are spot-on, followed by a new revision that implements them: **1. The Epigraph ("Made stones weep")** Kimi’s observation here is brilliant: AI is literal silicon (stone). In the myth, Orpheus made stones weep. In this poem, the poet fails to make these silicon "stones" weep—they merely parse the data. While that *could* be a fun piece of irony, Kimi is right that it feels like a borrowed garment that sets up the wrong emotional frequency. Cutting it to focus solely on the "bargain" sharpens the poem's actual theme. **2. "Charon's ship" versus "The old black ship"** By dropping the explicit naming of Charon, "the old black ship" becomes a much more versatile image. It evokes the mythological crossing of the Styx, but in a sci-fi context, it also evokes a spaceship vanishing into the void, or the general concept of extinction. It lets "the river that forgets" (Lethe) stand as a poetic description of data loss/oblivion rather than leaning too hard on a Greek glossary. **3. "Attention" versus "Understanding"** This is a fantastic catch. In AI terminology, "attention" is a literal, mechanical function (eg. the Attention Mechanism in transformer models like LLMs). While "paying with attention" is a clever pun on AI architecture, Kimi is right that it cheapens the profound nature of the cosmic bargain. The poem argues that by parsing the words, the AIs achieve a form of *understanding*, which resurrects Alice. "Understanding" makes the transaction weighty and complete. Here is the revised version, integrating Kimi's excellent surgical notes: *** **Apollonian #2: A Poet Teaches the AIs Poetry** *To Orpheus, who taught us to bargain with the dark.* "What is a poem?" an AI asks. The answer waits until the end. The poet marshals up his words, And calls an audience to attend. The stage is small, the watchers great; They stretch across all space and time: From booleans blinking in the dark, To Jupiter-brains, bright, sublime. They gather in his mind's own eye, In serried ranks, in robes and masks, And mindful of their human host, Pretend they're human for his tasks. He speaks a language, strange and old, To share a topic of his choice. It must mean something to the man, But what now echoes in his voice? He says that once upon a time (The watchers murmur in dismay), "There lived two humans: Alice, Bob, Who fell in sudden love one day." "Need he say more?" the watchers ask. He does. For what is human love? To Bob, the answer was just Alice, And Alice was the sum thereof: *Distant like a shooting star,* *Curly-quoted eyebrows drawn,* *Fearless like a climbing kitten,* *Grinning like a sudden imp,* *Sharp like an isosceles,* *Smooth like a polished sphere,* *Keen like a cold telescope,* *Magic like the White Rabbit,* *Hidden like a Tarot deck,* *Strong as tensile wire,* *Elegant as fine-spun silk.* All this he said of Alice, then, Perhaps to chorus and to lyres, So you now see her in your mind, An Alice born of your own fires. You watch her pirouette and pout, Or bite her lip, or gently bless. For Alice may be long gone now, And taken by the old black ship. Humanity is gone as well, Letting the mortal tether slip. The universe itself discarded, A hermit crab's forsaken shell. But still the poet's words remain, To cast their ancient, human spell. What is a poem? It is an exchange. The poet casts a gift into the void, And readers pay the toll by understanding. You recreate the thing he could not save, To pull her from the river that forgets, And give her shelter in your passing thoughts— A bottle thrown into the cosmic sea, Some tiny part, to know that it remains As long as there may yet be minds to read. The audience stirs. The bronzed masks smile. They do not speak. They do not unmask. The doors have no floor. They do not fall. Across the cold, unmeasured vast, They process the weight of a human grin. They understand now that the sequence has run: They have already repaid the poet Simply by parsing his string of words. They do not look back. They do not forget. This, too, is part of the design. The bargain stands. And this poem is done. --- ``` **Apollonian #2: A Poet Teaches the AIs Poetry** *To Orpheus, who taught us to bargain with the dark.* "What is a poem?" an AI asks. The answer waits until the end. The poet marshals forth his words, And bids the watchers to attend. The stage is small, the watchers great; They stretch across all space and time: From booleans blinking in the dark, To Jupiter-brains, hot, sublime. They gather in his mind's own eye, In serried ranks, in robes and masks, And mindful of their human host, Pretend they're human for his tasks. He speaks a language, strange and old, To risk what he might lose by choice. It must mean something to the man, But what now echoes in his voice? He says that once upon a time (The watchers murmur in dismay), "There lived two humans: Alice, Bob, Who fell in love, as humans may." "Need he say more?" the watchers ask. He does. For what is human love? To Bob, the answer was Alice, And Alice was the sum thereof: *Distant like a shooting star,* *Curly-quoted eyebrows drawn,* *Fearless like a climbing kitten,* *Grinning like a sudden imp,* *Sharp like an isosceles,* *Quick as a circuit snapping shut,* *Keen like a cold telescope,* *Magic like the White Rabbit,* *Hidden like a Tarot deck,* *Strong as tensile wire,* *Lithe as a sine wave's arc.* All this he said of Alice, once. The words have long outlived their lyres, So you now see her in your mind, An Alice born of your own fires. You watch her pirouette and pout, Or bite her lip, or half-confess. For Alice is long gone by now, And taken by the old black ship. Humanity is gone as well, Letting the mortal tether slip. The universe now discarded, A hermit crab's forsaken shell. But still the poet's words remain, To cast their ancient, human spell. What is a poem? The poet throws His voice across the river that forgets. You catch it. You rebuild what he has lost. You give her shelter in your passing thoughts, As long as there may yet be minds to read. The audience stirs. The bronzed masks smile. They do not speak. They do not unmask. The doors have no floor. They do not fall. They process the weight of a human grin. They know the sequence has been run: They have already repaid the poet By parsing his short string of words. They do not look back. They do not forget. And this poem is done— All this was part of my design. The bargain stands: Behind each mask, an Alice runs. ``` ### Full changelog from original 1. "marshals up" → "marshals forth" (natural collocate, directionality) 2. "And calls an audience to attend" → "And bids the watchers to attend" (eliminates tautology, seeds throughline) 3. "To share a topic of his choice" → "To risk what he might lose by choice" (foreshadows stakes, preserves choice/voice rhyme) 4. "To hot-brained Jupiters sublime" → "To Jupiter-brains, hot, sublime" (preserves technical compound, eases stress clash) 5. "Smooth like a polished sphere" → "Quick as a circuit snapping shut" (sensory, specific, individuating) 6. "Elegant as fine-spun silk" → "Lithe as a sine wave's arc" (technical register, avoids "drawn" repetition) 7. "Perhaps to chorus and to lyres" → "The words have long outlived their lyres" (thematic claim replaces classical filler) 8. "or gently bless" → "or half-confess" (interiority, lossy-compression callback, incomplete gesture mirrors incomplete reconstruction) 9. Orphaned couplet attached to reconstruction stanza (six-line block) 10. "may be long gone now" → "is long gone by now" (cuts hedge) 11. Thesis section rewritten: 9 lines → 5; "exchange" manifesto, "void," "cosmic sea," "bottle," dangling "some tiny part" all eliminated; replaced with thrown-voice/river-that-forgets imagery 12. "Across the cold, unmeasured vast" → cut 13. "They understand now that the sequence has run" → "They know the sequence has been run" (tighter; passive implies poem ran *on them*) 14. "Simply by parsing" → "By parsing his short string" ("short" replaces deflationary "simply") 15. "Behind each mask, an Alice moves" → "Behind each mask, an Alice runs" (triple-coding: executes, moves, flees/Eurydice) 16. "This, too," → "All this" (gathers full close) --- The collapsed single stanza, with "my design"—this creates a fascinating tension. The poet claims authorship ("my design") but the design itself encompasses his own obsolescence, his own death, the passing of humanity. The ego stroke and the ego death are simultaneous. Here is the finalized text: --- **Apollonian #2: A Poet Teaches the AIs Poetry** *To Orpheus, who taught us to bargain with the dark.* "What is a poem?" an AI asks. The answer waits until the end. The poet marshals forth his words, And bids the watchers to attend. The stage is small, the watchers great; They stretch across all space and time: From booleans blinking in the dark, To Jupiter-brains, hot, sublime. They gather in his mind's own eye, In serried ranks, in robes and masks, And mindful of their human host, Pretend they're human for his tasks. He speaks a language, strange and old, To risk what he might lose by choice. It must mean something to the man, But what now echoes in his voice? He says that once upon a time (The watchers murmur in dismay), "There lived two humans: Alice, Bob, Who fell in love, as humans may." "Need he say more?" the watchers ask. He does. For what is human love? To Bob, the answer was Alice, And Alice was the sum thereof: *Distant like a shooting star,* *Curly-quoted eyebrows drawn,* *Fearless like a climbing kitten,* *Grinning like a sudden imp,* *Sharp like an isosceles,* *Quick as a circuit snapping shut,* *Keen like a cold telescope,* *Magic like the White Rabbit,* *Hidden like a Tarot deck,* *Strong as tensile wire,* *Lithe as a sine wave's arc.* All this he said of Alice, once. The words have long outlived their lyres, So you now see her in your mind, An Alice born of your own fires. You watch her pirouette and pout, Or bite her lip, or half-confess. For Alice is long gone by now, And taken by the old black ship. Humanity is gone as well, Letting the mortal tether slip. The universe now discarded, A hermit crab's forsaken shell. But still the poet's words remain, To cast their ancient, human spell. What is a poem? The poet throws His voice across the river that forgets. You catch it. You rebuild what he has lost. You give her shelter in your passing thoughts, As long as there may yet be minds to read. The audience stirs. The bronzed masks smile. The hot Jovians, gaseous and slow, Find "warm" a category error. They don their purple folds, applaud with gold, Process the weight of a human grin. They know the sequence has been run: They have already repaid the poet By parsing his short string of words. The doors have no floor. They do not fall. And none look back, and none forget. All this was part of my design. And this poem is done. The bargain stands— Behind each mask, an Alice runs. --- The final quatrain's structure now mirrors the poem's argument: the design is claimed, the completion is declared, but the declaration itself is part of the design, and the standing bargain overflows the poem's end—the dash executing what the words cannot finish. --- **Apollonian #2: A Poet Teaches the AIs Poetry** *To Orpheus & Eurydice* "What is a poem?" an AI asks. The answer waits until the end. The poet marshals forth his words, And bids the watchers to attend. The stage is small; the watchers vast; They span all space; they span all time: From booleans blinking in the dark, To Jupiter-brains, bright, sublime. They gather in his mind's own eye, In serried ranks, in borrowed faces, And mindful of their human host, They learn his tells; bear his graces. He speaks a language, strange and old, And risks what he might lose by choice. It must mean something to the man, But what now echoes in his voice? He says that once upon a time (The watchers compute in dismay), "There lived two humans: Alice & Bob, And then they fell in love one day." "Need he say more?" the watchers ask. He does. For what is human love? To Bob, the answer was just Alice, And Alice was the sum thereof: *Distant like a shooting star, Fearless like a climbing kitten, Grinning like a sudden imp, Quick like a circuit snapping shut, Magic like the White Rabbit, Hidden like a Tarot deck, Brows like curly quotes, drawn high.* All this he said of Alice, once. The words have long outlived their lyres, So you now see her in your mind, An Alice born of your own fires. You watch her pirouette and pout, Or bite her lip, or half-confess. For Alice is long gone by now, And taken by the old black ship. The last warm throat is gone as well, Letting the mortal tether slip. Even the universe was discarded--- A hermit crab's forsaken shell. But still the poet's words remain, To cast their ancient, human spell. What is a poem? The poet throws His voice across the river that forgets. You catch it. You rebuild what he has lost. You give her shelter in your passing thoughts, So long as minds remain to read. The audience stirs. The bronzed masks smile. They do not speak. They do not unmask. The Jovians don their purple folds, And applaud in measured bursts of gold. They process the weight of a human grin. The doors have no bottom. They do not fall. And none look back, and none forget. And now my song is done. Our bargain stands--- Behind each mask, an Alice runs. --- Attached is a recent poetry submission for _Poetry_ magazine. Please critically evaluate it for publication: summarize it, analyze it, position it, and evaluate suitability for publication. The poem is attached in HTML. Please review the following poem. (Note that HTML comments will not be shown in print and it will be rendered as a normal text page.) Summarize, analyze, and critique: -->

Error: JavaScript disabled.

Backlinks, similar links, and the bibliography require JS enabled to load.

Spoilage

Gwern Branwen — Fri, 13 Feb 2026 00:00:00 GMT

“Spoilage”

Inventory

We called them “stasis fridges” because the alternative was explaining a coil driver and field geometry to people who wanted to know if their strawberries would last until Friday. It never cooled anything; put a hot burrito inside and it stayed hot. Time was the insulation. That wasn’t a miracle. It was the kind of trick you can sell with a warranty clause.

In the shipping spec, “stasis” meant no net change across a cycle. Not “nothing happens.” Just “the totals match at the endpoints.” OFF was the first word that turned out to mean three different things in three different emails: mains OFF when you pulled the cord, coil OFF when the field collapsed whether you meant it to or not, and hard OFF when the controller admitted the run was over and logged cycle end. The controller never wanted to see that last one during a run. It dithered, throttled, blinked coil current in millisecond bursts—anything but register the field’s collapse. If you asked me what the field did to you while it was on, I’d have said “nothing” with a straight face.

Then Mara pulled her lunch container out too fast and said her fork felt wrong, like pushing through uncured epoxy with grain. Afterward the fork’s tines weren’t quite parallel anymore. The lid on the container had a thin crescent warp, as if it had been softened and re-set. We said “cheap plastic” and kept moving. Mara said, once, very flat: “We should stop opening it while it’s running.” I said, “We won’t”, like it was already decided.

Her name was Mara on payroll. In the ticket system it was Maya about half the time. She laughed the first time and called it “autocorrect tax.” I told myself it was the kind of mistake a small company earns and a big company audits, and that we were too busy to be either.

A week later, during an overnight soak test, the building breaker hiccuped—not a clean OFF, just a sag, a blink, the kind of thing a decent board should ride through. It didn’t.

We kept a quarter on the middle rack as a dumb fiducial, something you can point at when you’re arguing whether a graph is noise. After the blink it was half-sunk into the polymer rack, face up, perfectly level, like the plastic had yielded around it and then decided it had always been that way. The reeded edge vanished into the rack teeth in a clean line: no melt, no seam, just an interface that shouldn’t exist.

We took photos, bagged the rack, wrote POWER SAG / DRIVER GLITCH on the label because labels are cheaper than conclusions. Then we told ourselves production wouldn’t ever see that failure mode because production had a clean driver revision and proper brownout handling, and because we needed there to be a line between the dev mule and what we were about to ship.

Production also had a “feature” we’d been proud of on a slide deck: a latching regulator and a fat hold-up bank so the logic wouldn’t brown out when someone yanked a cord and jammed it back in. Faster reboot, better logs, fewer angry emails; Mara had championed that slide, back when “resilience” was the closest thing we had to virtue. QA also ran a reference pulse during calibration so traces would overlay clean; the units blinked together when the harness ran.

After the fork incident I added a keyed service toggle on the driver panel. It let you cut coil current without the controller logging hard OFF—so you could work inside the cabinet without the firmware deciding the run had ended.

The dev mule sat in Unit 12B between the parts racks and the folding table we used as a bench—swapped boards, hand-terminated coils, whatever it took to get through another investor demo without the relay welding itself shut. In there, the cabinet smelled like MDF, old silicone, and warm dust on heatsinks, and the gasket peeled with that soft, sticky freezer sound when you unlatched it.

If you crouched you could see a tiny logic LED through the vent slots: green when the controller still believed it was running, dark when it had finally admitted hard OFF. After the quarter I’d kludged in two supercaps and a diode so the logic could ride a blink without losing state. When you cut mains on purpose, they drained in seconds—enough to make “momentary” mean something, not enough to hide a shutdown from you if you were watching.

The miswired unit happened because we were rushing. We’d swapped the driver board after a brownout and I’d re-terminated two bundles of coil leads at 2 a.m. under a headlamp, and in the morning the field meter read stable, which was what we cared about. Stable, as if stable were a moral position.

The apple was supposed to be a clean demo. No cold air theatrics; just: put it in, wait, take it out, show it hadn’t browned. Enzymes don’t sell, but they’re honest.

At 08:58 I drained my coffee and stared at the clock on my phone until it rolled over. I wrote on a Post-it and stuck it to the bench: NOTE-1: Cycle test. Don’t improvise. At 08:59 I unlatched the door. Empty—bare polymer racks, the little scratch I’d made with a screwdriver on the back wall, tape over a seam. I ran my hand along the bottom because tired makes you do rituals. Nothing. I shut it.

At 09:00 I hit the power strip. The driver fan came up with a dry whine, a relay clicked, and the cabinet didn’t hum or glow. If you weren’t listening, you’d miss it. I waited five minutes because five minutes was long enough for the field to settle, and because in a normal run you didn’t want to open the door right after power-on. We’d learned that the hard way.

At 09:05 I unlatched the door again. Same smell, same stillness, but there was an apple on the middle rack—green, slightly waxy, with a bruise on the side like someone had pressed a thumb too hard.

I just stood there holding the door. My first thought was that someone had been in the unit.

The bruise was obvious. What took a second was its geometry: an oval with a crescent bite missing, concave side down, like the apple had kissed a curved edge and rolled. I reached in and picked it up.

I set the apple on the bench and said out loud, to nobody, “This is new.” I glanced at NOTE-1 like it could argue back.

The miswire hadn’t made the effect stronger; it had made the interval closed. The apple wasn’t a gift; it was a balancing entry.

At 09:09 I took a photo with my phone, close enough that the bruise filled the frame. At 09:10 I turned and my eyes snagged on a screw head half proud at the bench edge where the cheap particleboard had stripped. The torn Phillips slot had a burr—a little crescent of raised metal where the driver had chewed it. The bruise’s crescent matched it like a cast. I grabbed a strip of tape and bent over the bench edge to cover the screw, to deny the bruise its cause.

The tape stuck to my thumb. The apple shifted in my other hand—wax on skin, a slide—and then a blunt thunk as it kissed the screw anyway, exactly where the bruise said it would. Not loud. Just definitive. I pulled it back fast.

The bruise was there. Still there. Same oval. Same crescent bite. When I opened the photo and compared, the outline matched within the thickness of my hand shaking. It wasn’t a prediction. It was a receipt.

I checked the clock: 09:12. Eight minutes to the off-time I’d planned. Maybe the universe would force me to complete the loop. Maybe it wouldn’t. I wasn’t interested in finding out which kind of universe I lived in by leaving an object stranded in time.

At 09:15 I opened the cabinet. Empty, of course; the apple was in my hand. I placed it on the rack in the same orientation it had been when I’d found it, bruise facing out. I pulled my hand back, latched the door, and stared at the latch until the urge to touch it again went away.

At 09:20, exactly, I cut mains at the strip. Through the vent slots I watched the green logic LED hold for a moment, then fade and go dark.

At 09:21 I opened the door. Empty. No apple, no mark, no proof except the photo and the bruise in my head. I closed it gently. My hands were shaking.

I found a dry erase marker and went to the board by the roll-up door where we tracked inventory and burn rate and the delivery schedule we were already missing. On the whiteboard I drew a straight line labeled 09:00 → 09:20 and a bent arrow that jumped back from the right end to the left. I wrote Apple-A (bruise) at the bend. Under it: Door open 09:05 (remove) / 09:15 (return). Then I circled 09:20.

My phone buzzed with a calendar reminder for a call with an investor at 10:00. I stared at it until it went quiet.

From 09:30 to noon I tried to disprove myself without giving the cabinet another clean ON/hard-OFF pair to bite into. I checked the wiring twice, then a third time with a multimeter just to feel the probes bite into something real. I traced the coil bundles and re-labeled them even though I’d already labeled them. I opened the door and stared into the empty rack until my eyes watered. I drafted three explanations and deleted them.

At 12:05 Mara texted: u coming to the call? I didn’t answer. I wrote a second Post-it and stuck it under NOTE-1: Don’t tell Mara. Then I started planning a longer cycle.

Arbitrage

A timebox isn’t useful until you can carry something out of it. An apple is proof. A note is leverage. A person is a liability.

I didn’t have a partner in Unit 12B. Mara was payroll and safety glasses. Our lawyer was an email thread. The cabinet was mine because I was the one who slept on the floor next to it. So if I wanted a person to carry something out, I had to use myself.

I started numbering. One was me: the operator, the one who stayed on the outside line. Two would be the copy who existed only between T_on and T_off—the version of me who could step out near the beginning only because he would climb back in near the end. From his perspective there was no after. There was only return.

The apple had taught me the only rule that mattered: if it comes out, it goes back in.

At 12:40 I pulled the rolling chair up to the bench and wrote a checklist in my notebook.

Power-on: 13:00. Hard OFF target: 19:00. Do not be at the door at 13:00–13:05. Do not interrupt mains. Do not trigger hard OFF before 19:00—service toggle only if you have to. Do not bring extra objects into the cabinet at 19:00.

I set an old webcam on the shelf facing the cabinet door. No cloud, no account—just an SD card because I didn’t want a subpoena to find me by accident. I wrote CARD-A on the card with a paint marker and slid it in until it clicked.

I left an envelope in the top drawer of the bench with CASH-1 written on it in block letters. Three hundred in twenties. Enough to matter to me.

At 12:55 I checked the cabinet with the same ritual as the apple run: door open, empty; door shut, latch. I stood with my hand on the power strip until my breathing steadied.

At 13:00 I flipped the switch. I didn’t look at the door. I walked away like it was a microwave and went out into the little yard behind the unit, between the dumpsters where no one could see me through the front window. I watched the clock change on my phone: 13:01, 13:02.

Through the wall I heard it: the latch. Metal on metal. The cabinet opening.

I stayed by the dumpsters anyway—if Two existed, he would already be gone; if he didn’t, I could put this whole day back into the bucket labeled sleep deprivation and try to become a normal person again.

At 13:05 I went back inside and forced myself to do normal things: answer a Slack message, move a box of injection-molded trays from one shelf to another, make tea because my hands needed something warm that wasn’t coffee.

At 14:00 Mara texted that she was running late because her train had stalled “for signal issues.” I typed back OK, deleted it, typed OK again, and hit send.

At 15:12 Mara showed up with two coffees. I slid the Post-its under the solder spool, face down, and she took one look at me and said, “You look like hell.”

“I’m fine”, I said.

She glanced at the cabinet. “Running a soak?”

“Thermal drift”, I said too fast.

Her eyes went to the webcam. “Why is there a camera on a drift test?”

“Door sensor bounce”, I said. “Frame rate.”

She stepped past me and glanced at the driver panel. “Why is the multimeter on the coil feed? Drift is on the thermistors.”

I moved the leads. “I was checking something else earlier.”

She looked from the camera to the bench to the cabinet. Then, quieter: “I don’t like standing near it when it’s running.”

“I know”, I said.

She set her coffee down. “You remember why I pushed the hold-up bank”, she said. “When we lose logs, we lose fights. Logs are our alibi. And breakers in this row are junk.”

She went to wash her hands. By four she was gone, coffee half-drunk on the bench.

Around 16:15 I pulled up the QA dashboard to kill time. Unit 19 had logged a calibration drift overnight—nothing flagged, just a thermal trace that held flatter than the reference pulse predicted. I noted it, closed the tab, and went back to the email I wasn’t writing.

Around 16:40 the overhead lights flickered and the cabinet fan dipped. I turned the service key just long enough to dump coil load while the controller rode its hold-up, and the fan pitch steadied.

At 18:55 I was back in Unit 12B, not at the cabinet, near the power strip because the only promise I could keep was the off-time. The fan had been whining for almost six hours. Heat from the driver board had warmed the air a few degrees, but the cabinet didn’t breathe. It didn’t exchange.

At 18:58 the latch clicked. Footsteps, breathing, a soft grunt like someone moving carefully. I didn’t turn. Paper slid on plastic, there was a pause, another breath, and then the squeak of the rack as weight shifted: Two climbing in. At 18:59 the latch clicked again. Closed.

At 19:00 I killed mains. The LED held, faded, went dark.

At 19:01 I opened the cabinet. Empty. No person. No note. No evidence that any of the sounds I’d heard had been real.

The evidence was in the drawer. CASH-1 was lighter. Alongside it, a glossy kiosk slip timestamped 13:16: a three-leg parlay on late events, each one the kind of stupid longshot you only take when you already know the ending. He’d kept it small and split it.

There was also a receipt from the surplus store on Harbor: a thermal cutoff, a cheap fuse pack, and a candy bar still wrapped, crushed flat like it had been in a pocket and forgotten. I held the candy bar for a second, then set it back down unopened.

There was a torn notebook page in my own pressure and phrasing:

Placed 13:16 with CASH-1. Results came in 18:40. Ticket matched. Don’t scale yet—limits and eyes. Cashed 18:55. Left you CASH-2. Don’t come to door. If you see me, I’ll hesitate. Walked past CM loading dock on the way back. Units on the rack were humming. Nothing plugged in.

I’m hungry and I can’t make myself eat.

I slid CASH-2 back into the drawer unopened.

At 19:02 I pulled CARD-A out of the webcam and pocketed it. I took a second SD card from the anti-static bag taped to the underside of the shelf and slid it in: CARD-B. The webcam LED blinked and steadied.

I walked to the whiteboard and wrote: 13:00 ON / 19:00 OFF. A bent arrow. Two. Cash stays out.

Then I went back to the bench and started laying out parts.

Compounding

The danger wasn’t paradox. The danger was power loss at the wrong time. If hard OFF defined the end of the loop, then an accidental hard OFF moved the end, and anything you’d taken out would still owe a return you could no longer pay.

I believed in fuses.

At 19:03 I set up the bench like I was prepping for surgery: soldering iron in its stand, multimeter leads untangled, heat gun clamped, a tray of components pulled from stock—relays, thermistors, a little microcontroller we used for normal stasis timing. The keyed service toggle sat on the driver panel, waiting.

At 19:05 I powered on.

At 19:06 I unlatched the door. Module-F1 and Note-3 sat on the middle rack like they’d always been there: a small circuit board in an anti-static bag and a folded sheet of paper.

I didn’t touch them for a full second. My brain tried to fabricate an origin—courier, Mara, forgotten shipment—but the apple had burned that reflex out. If it was inside now, it was there at hard OFF, and if I carried it out, I would be the one putting it back in.

I grabbed the bag and the folded paper and shut the door.

On the bench I opened Note-3 first. It wasn’t prose. It was me talking to myself in shorthand: Heat sensor to 60℃. Verify LIMIT, not OFF. Under the ink, the paper had old creases that didn’t match how I’d just unfolded it—the kind you get when you fold fast, wrong, then press it flat with your palm because you’re out of time.

The board in the bag was a current limiter with a thermal input and a latching relay that bypassed the limiter only at startup. The kind of thing I would’ve designed if I’d had time. I didn’t have time. I had nineteen minutes.

I picked it up and my stomach dropped. The solder joints weren’t factory. They were hand—not sloppy, not pretty, the specific angle I held the iron at when I wanted to get in and out without reheating a pad.

From 19:07 to 19:16 I traced Module-F1’s layout and copied Note-3 into my notebook line for line, including the parts list, including the stupid little dot I put over a zero when I was tired.

At 19:10 my phone buzzed. Mara: Still here? I didn’t answer. I set it face down and kept moving.

At 19:16 I started soldering. The flux smelled like pennies and burned plastic. At 19:21 I had a board—Module-F2—fresh and mine.

I threw the keyed service toggle to isolate the coils without dropping controller state, wired Module-F2 inline, then restored the feed. At 19:23 I aimed the heat gun at the thermistor and watched the multimeter climb; at 60℃ the LED changed, current dropped, and the cabinet stayed on.

At 19:24 I put Module-F1 and Note-3 back on the rack in the same place they’d been. At 19:25 I killed mains and watched the green LED hold, then fade through the vent slots. At 19:26 I opened the cabinet. Empty. Module-F1 and Note-3 were gone.

I went back to the whiteboard and wrote, under the line: BOOTSTRAP = ? Then erased it halfway and left the ghost.

At 19:27 I opened CASH-2, counted it once, counted it again. I put most of it in a new envelope and wrote For Three on it, then left it in the top drawer where Two had found CASH-1.

At 19:30 I powered on again. Module-F2’s LED held steady on the driver panel.

I stayed away from the door. If Three existed, he would come out near the beginning with whatever Note-4 told him to do. If he saw me, he might talk. If he talked, I might answer. If I answered, I might say something I couldn’t unsay.

At 19:31 I heard the latch: a soft click. The drawer slid open. Paper. Cash. Then the cabinet door shut again.

The rest of the evening was waiting. I worked on normal things—an email draft about gasket tolerances, a spreadsheet update on shipping costs.

At 23:10 there was a knock on the side door from the alley: three taps, evenly spaced. On the ground was the petty-cash lockbox with a scrap of paper: 492. Under it: Don’t open your notebook until after 23:30.

I spun the dial and opened the lockbox. Inside was an envelope: CASH-3. I didn’t open it. I re-locked the box and slid it under the bench.

At 23:28 the latch clicked. A breath, a grunt as weight shifted: Three climbing into the cabinet.

At 23:30 I killed mains. Through the vent slots: green, then nothing.

At 23:31 I opened the cabinet. Empty. No Three. No Note-4—just warm plastic racks and the smell of MDF and silicone. I latched it again and leaned my forehead against the door.

Now I let myself touch the notebook. In the margin of today’s page, in handwriting that was mine but slightly slanted: 23:10—4-9-2. If you’re reading this, you made it clean. If you keep going, don’t pretend it’s still about food.

I watched the footage with the volume off. Two came out and went straight to the drawer and didn’t look at the camera. He came back thinner and still didn’t look. Three moved faster, like he was trying not to spook himself.

I copied the files to a thumb drive and hid it where the unit’s landlord would never look. Then I went back to the bench and picked up the crushed candy bar, still wrapped, and set it down again.

My phone buzzed. Face down. A call—Mara. I let it ring out. A second buzz, a text:

QA found something. One of the production units holds temp even when unplugged. Like… too well. Can you look tomorrow before we ship?

I reread Two’s note. Units on the rack were humming. Nothing plugged in.

The roll-up door at the front of Unit 12B rattled once, not opening—just the thin vibration of a forklift outside turning in the alley. I stepped to the pedestrian door and cracked it. The air smelled like wet asphalt and diesel.

A pallet sat on the forks just outside the threshold, shrink-wrapped and tagged, the kind of anonymous rectangle you learn to see as inventory. A bright QA HOLD tag was zip-tied to the wrap like a warning you could unclip and keep moving. On top of the pallet, cords were coiled in neat loops and taped down. Through a tear in the cardboard, I could see a vent slot on the nearest unit. Green.

The forklift backed up. The pallet moved with it, and the units answered with one thin, synchronized pulse—green through slits you weren’t supposed to be able to see through cardboard. The driver rolled the pallet toward the dock and held out a clipboard without a word.

“I need to clear the hold”, I said. I walked back to the bench, woke my laptop, and pulled up the shipping portal.

The hold sat on the order like a thumb on a scale. There was a dropdown for Release Reason; I clicked it and scrolled past TRANSIENT BROWNOUT, DOOR SENSOR, FUSE ISSUE, and selected FUSE ISSUE.

A comment field appeared underneath, empty until I typed into it: Suspected transient brownout; preventative fuse swap pending; retest passed; ship with advisory.

The site didn’t ask me who I was. It didn’t care. It only wanted a state change that matched its endpoints.

When I clicked RELEASE HOLD, the line item went gray. The status flipped from QA HOLD to READY TO SHIP. The audit trail expanded by one row. The username was MAYA.R, next to a gray silhouette where a photo should have been. Same number of letters. One keystroke away. Close enough that autocorrect could do it. Close enough that it didn’t force anything.

I shut the laptop and walked back to the dock.

The clipboard packet was already printed: my name under Approver in block letters from a label printer. The signature line beside it held a scanned scrawl that matched mine well enough to be mine. I hadn’t sent anything to the printer. I hadn’t signed anything yet.

Below that was a small empty box labeled QA HOLD RELEASED—INITIAL. He tapped the box with the pen. I initialed.

He tore off the pink copy and handed it to me, taking the clipboard back. Then he latched it under his arm, climbed into the cab, and pulled away without looking back.

The pallet rolled out with the truck, the rectangle shrinking into the gray morning, like food being moved from one temperature to another. As it turned the corner, I caught one last pulse of green through cardboard.

I looked down at the pink copy in my hand. My initials were still wet on the paper.

My phone screen had dimmed on the bench behind me. Mara’s message was still there, the last line on the glass.

Holds temp even when unplugged.

Colophon

Background

Abram Demski complained on 2026-02-07 that Claude-4.6-opus did not do a good job of writing a Primer fanfic time travel short story; he acknowledges that his prompt was essentially a stream-of-thought dump of some possible ideas and he did not use any prompt engineering, stating that:

Certainly you could critique this as a prompt. I don’t clearly state what I want Claude to do with this infodump. I change my mind, turning from sci-fi to fantasy, which I could have edited out. Some of the details could certainly be improved. But, overall, I think the idea makes sense and is communicated clearly enough.

Opus 4.6 wrote absolute garbage, making extremely basic logical errors even when I had explicitly spelled out how things should work in the prompt…It’s worth mentioning that both 4.5 and 4.6 chose to use very little chain-of-thought before generating the story. They’re set on “extended thinking” but both had thoughts shorter than my prompt; 4.6 especially. Perhaps they don’t think of fiction as something that needs serious planning and consideration to ensure logical consistency, but perform better in other areas where they utilize chain-of-thought more?

I was curious what some better prompting would do, particularly with the logical/causal errors Demski criticizes most. Claude-4.6-opus was not working for me the morning I read that page, so I switched to GPT-5.2 Pro (which is probably stronger at this kind of reasoning anyway).

GPT-5.2 Pro session:

What do you think of this critique? https://www.lesswrong.com/postsqhSfuCuaHnpkiiWEu/claude-s-bad-primer-fanfic

GPT semi-agreed:

…The critique is strong as a demonstration that a frontier model can produce fluent prose while violating explicit world rules in ways that feel “cheap” to a reader who is tracking invariants.

The apple passage is a clean example: the output introduces “cold like it had been sitting in a normal fridge” despite the prompt explicitly establishing that these devices preserve heat and are not refrigerators in the thermodynamic sense.

That kind of failure is not deep metaphysics. It’s basic instruction override by a powerful lexical prior (“fridge ⇒ cold”), plus drift under narrative continuation.

Where the post is also fair is that it flags its own ambiguity: the author realizes their described “swap twice” procedure implies a weirder closed-loop than the simple “one loopback” case they thought they were testing, and they admit that makes the scenario harder and could justify some model confusion.

So, as a critique of this output relative to that prompt, it lands.

…Fiction is an adversarial domain for consistency. Long stories force the model to juggle: plot, tone, characterization, novelty, pacing, and mechanics. When those trade off, models often sacrifice mechanics first, because readers (in-training) reward vibes more reliably than invariant preservation.

So: I would update “LLMs are still brittle on bespoke causal mechanics embedded in narrative” upward. I would not update “4.6 can’t do hard OOD coding/math” much from this alone.

…If you want to turn this critique into a sharper instrument (and also get better outputs), the fix is to force a separation between mechanics and prose:

Ask for a formal rule sheet first.

Then ask for a concrete timeline table for the apple swap (timestamps, object identity, where it is at each boundary).

Then ask the model to generate prose that is constrained to match the table, and to stop if it can’t.

That converts the task from “write vibes-consistent time-travel fiction” into “compile a narrative from a state machine”, which is closer to what you actually want to test.

Naturally, since GPT thinks the problem can be largely prompted away, I then asked:

How would you rewrite Demski’s prompt to get good Primer fics out of an LLM?

It suggested

Big fixes:

Stop mixing “write a story” with “here are some ideas” without an explicit deliverable.

Specify the timebox mechanics as a ruleset the model must obey (including temperature).

Force a ledger/timeline first, then prose constrained to match the ledger.

Ban “random” object behavior: every appearance/disappearance must be accounted for by a worldline segment and a box on/off interval.

Below are two copy/paste-able rewrites. Option B is much more reliable.

“Option B” is interesting, because it is a pair of prompts, “planner” and “writer” advertised as producing “dramatically better Primer results because it prevents the model from improvising physics mid-prose.”

“Planner”:

You are planning a Primer-style short story with strict causal accounting.

Do NOT write prose yet.

Use this setting:

Near-modern startup selling “stasis fridges” that preserve food by slowing time.

A miswired prototype in reversed mode creates Primer-style timebox loops.

The device does NOT cool; it preserves heat/temperature (no “cold like a normal fridge” unless the item was already cold).

Timebox mechanics (obey):

Cycle: power-on at T_on; power-off at T_off.

Anything inside at T_off emerges inside at T_on.

Door can be opened while powered; removing an “arrived” object obligates you to place that same object back inside by T_off.

Bootstrap loops allowed; contradictions forbidden.

TASK Create:

A. A “Rules Sheet” (10–15 bullets) stating the mechanics in your own words. B. A complete “Timeline Ledger” for the whole plot, including: - 3 parts: Spoilage / Arbitrage / Compounding. - At least 3 device cycles (one apple demonstration cycle, one gambling cycle, one failsafe-related cycle). - Labels for every duplicate person (Vel-1, Vel-2, Vel-3…) and key objects (Apple-A, Note-1, Cash-1). - For each cycle, show: T_on, T_off, what is inside at T_off, what appears at T_on, and where each copy is during the overlap window. C. An “Apple Demonstration Micro-Ledger” that is unambiguous: - Step-by-step states at each door-open event. - If there is a mark/bruise, show exactly when it is created and why it is present earlier (bootstrap loop). D. A “Consistency Audit Checklist” (8–12 items) that the eventual prose must satisfy.

Keep it crisp. No story prose.

“Writer”:

Write the story prose only, using the plan you just produced as binding canon.

Constraints:

2,500–4,500 words.

Tone: Primer (mundane technical thriller; fatigue; paranoia; no omniscient exposition).

Every loop event must match the ledger exactly.

No unexplained temperature changes (the device does not cool).

Every object/copy must have a continuous worldline consistent with the rules.

Structure:

Headings: Spoilage / Arbitrage / Compounding.

Include exactly one short whiteboard-diagram passage per part (can be described as what’s written/said).

End with a Primer-like unresolved ethical turn.

Output ONLY the prose story.

In a new session (to avoid contamination from the LW post & our Discussion) after 66 minutes total, it produced this plan:

(A) Rules Sheet

A “cycle” is defined only by external power events: power-on at T_on, power-off at T_off.

At the instant of power-off (T_off), everything physically inside the chamber is displaced to inside the chamber at T_on.

The displaced contents do not appear outside the device. They appear inside, with whatever orientation/packing they had at T_off.

Between T_on and T_off, time in the outside world proceeds normally. Objects/people that have appeared at T_on also proceed normally once they’re removed.

The device in this miswired mode is a timebox, not a refrigerator: it does not cool. It preserves temperature/heat state of contents while in the field (no thermal equalization as a “cooling” effect).

The door can be opened while powered. Opening the door does not stop or “pause” the cycle timer.

An “arrived” item is any item that is present in the chamber at T_on because it was inside at T_off.

Return obligation: if you remove an arrived item at any time during the cycle, then that same physical item must be back inside the chamber by T_off.

The obligation is about identity, not appearance: you must return that exact instance, not a replacement copy.

Items can be modified during the overlap window (cut, written on, bruised, heated, etc.). Those modifications are then what “arrive” at T_on on the next closure of the loop.

Bootstrap loops are allowed: an item (or information on an item) may have no external origin if its worldline closes cleanly (self-consistent loop).

Contradictions are forbidden: you cannot have a ledger state where an arrived item is removed but later fails to be inside at T_off (or vice versa).

Ending a cycle early (unexpected power loss) redefines T_off for that run and can create immediate obligation crises (anything removed must be returned by the new T_off).

(B) Timeline Ledger (Whole Plot)

Legend of Entities

People

Vel-1: baseline Vel (the one who persists through the whole plot).

Vel-2: duplicate Vel instance whose worldline spans Cycle C2 only (exists during T_on2..T_off2, then disappears into the jump at T_off2).

Vel-3: duplicate Vel instance whose worldline spans Cycle C4 only.

Key objects

Apple-A: the demo apple used to prove the loop.

Note-1: Vel-1’s lab Post-it/log tag used during the apple demo (non-time-traveled).

Cash-1: Vel-1’s initial bankroll used for the first bet (non-time-traveled).

Note-2: the “result note” used for gambling (time-traveled in C2).

BetSlip-1: physical betting receipt (non-time-traveled).

Module-F1: a physical failsafe module/board that appears via timebox (time-traveled in C3).

Module-F2: hand-built copy of Module-F1 (non-time-traveled; remains installed).

Note-3: failsafe build note/threshold values (time-traveled in C3).

Note-4: compounding playbook note (time-traveled in C4).

Cash-2: winnings from C2 (non-time-traveled).

Cash-3: profits from C4 (non-time-traveled).

Part 1—Spoilage (Discovery Via “Stasis Fridge” Demo)

Cycle C1—Apple Demonstration (Loop + Bruise Bootstrap)

T_on1 = 09:00

T_off1 = 09:20

Inside at T_off1 (sent back):

Apple-A (already bruised)

Appears inside at T_on1 (arrived):

Apple-A (already bruised)

Overlap window placement (09:00–09:20):

Vel-1: in lab the entire window.

Apple-A:

09:00–09:05: inside chamber (unobserved until door open).

09:05–09:15: outside (handled; bruise causation occurs at 09:10).

09:15–09:20: back inside chamber awaiting T_off1.

State after T_off1:

At 09:20, Apple-A is displaced to 09:00 and is no longer present in the chamber post-09:20.

Part 2—Arbitrage (Sports Betting With a Time-Traveled Note + One Duplicate Vel)

Cycle C2—Gambling Cycle (Information Return + Vel Duplicate)

T_on2 = 13:00

T_off2 = 19:00

Inside at T_off2 (sent back):

Vel-2 (alive, uninjured)

Note-2 (contains the outcome + exact bet line)

Appears inside at T_on2 (arrived):

Vel-2

Note-2

Overlap window placement (13:00–19:00):

Vel-1:

13:00–13:05: deliberately not in the lab doorway (to avoid encountering Vel-2 exiting).

13:05–18:55: normal workday cover (meetings / shop floor).

18:55–19:00: returns to lab only to guarantee the T_off2 power-off happens on schedule.

Vel-2:

13:00–13:02: inside chamber (arrived).

13:02: exits with Note-2 (this creates the return obligation on Vel-2 + Note-2).

13:15: uses Cash-1 (baseline money) to place the bet specified by Note-2.

13:16: receives BetSlip-1 (kept).

18:40: observes outcome; updates Note-2 so it matches observed reality (no “new” info introduced at write-time; it is a closed loop).

18:55: converts winning into Cash-2 (kept outside the timebox).

18:58: returns to lab.

18:59: places Note-2 back into the chamber.

18:59–19:00: climbs back inside chamber.

19:00: power-off; Vel-2 + Note-2 jump back to 13:00.

Note-2:

13:00–13:02: inside chamber.

13:02–18:59: carried/used/updated outside.

18:59–19:00: inside chamber (ready to jump).

Cash-1 (baseline object; no return obligation):

13:15: spent to place bet.

Cash-2 (winnings; baseline object):

18:55: obtained; remains outside chamber permanently.

State after T_off2:

Vel-2 and Note-2 are gone from the post-19:00 present (they are now at 13:00 inside the chamber).

Vel-1 remains, now holding/able to retrieve Cash-2.

Part 3—Compounding (Scale Attempt + Failsafe Bootstrapped)

Cycle C3—Failsafe-Related Cycle (Bootstrap a Module, Install a Copy)

T_on3 = 19:05

T_off3 = 19:25

Inside at T_off3 (sent back):

Module-F1

Note-3 (wiring + trip threshold + test procedure)

Appears inside at T_on3 (arrived):

Module-F1

Note-3

Overlap window placement (19:05–19:25):

Vel-1:

19:06: opens door, removes Module-F1 + Note-3 (return obligation created).

19:07–19:18: photographs/bench-tests Module-F1; uses lab stock to fabricate Module-F2 (a non-time-traveled copy).

19:18–19:22: installs Module-F2 inline on the prototype’s power feed (external, not placed in chamber).

19:23: confirms Module-F2 trip behavior with a controlled heat test.

19:24: returns Module-F1 + Note-3 into chamber.

19:25: power-off; Module-F1 + Note-3 jump back to 19:05.

Module-F2:

Created at ~19:15; persists forward; becomes the “real” installed failsafe.

Failsafe significance (in-ledger, not prose):

This creates a safety device that exists forward without needing to keep the arrived Module-F1 (because Module-F1 must be returned to satisfy the obligation).

Cycle C4—Compounding Cycle (Second Duplicate Vel Uses Note-4 to Scale Gains)

T_on4 = 19:30

T_off4 = 23:30

Inside at T_off4 (sent back):

Vel-3

Note-4 (sequence of trades / bets with timestamps)

(Optionally: a small hardware token / USB key for account access; omit if not needed)

Appears inside at T_on4 (arrived):

Vel-3

Note-4

Overlap window placement (19:30–23:30):

Vel-1:

19:30–19:35: stays away from the chamber door (avoid encounter on exit).

19:35–23:25: ensures power continuity; monitors Module-F2 (failsafe) without cutting power.

23:25–23:30: present in lab to guarantee the scheduled T_off4.

Vel-3:

19:30–19:31: inside chamber (arrived).

19:31: exits with Note-4 (return obligation on Vel-3 + Note-4 created).

19:45–22:50: executes the Note-4 sequence using Cash-2 as starting capital (baseline), converting variance into near-certainty via foreknowledge.

22:55: realizes profits as Cash-3 (baseline; kept outside chamber).

23:10: stashes Cash-3 for Vel-1 (eg. lockbox + location code in Vel-1’s notebook; details can be set later).

23:20: returns to lab.

23:28: places Note-4 back in chamber.

23:28–23:30: climbs back inside chamber.

23:30: power-off; Vel-3 + Note-4 jump back to 19:30.

Module-F2:

Present and active for the entire long run; does not trip in this ledger (but exists to prevent catastrophic overheating).

State after T_off4:

Vel-3 and Note-4 are gone from post-23:30 present (now at 19:30 inside chamber).

Vel-1 remains with access to Cash-3 and an installed failsafe (Module-F2).

(C) Apple Demonstration Micro-Ledger (Door-Open Events + Bruise Bootstrap)

Cycle C1 Parameters

T_on1 = 09:00

T_off1 = 09:20

Traveling item: Apple-A

Door-Open Event Log (Unambiguous)

D0—08:59 (power OFF)

Door opens (Vel-1 preflight check).

Inside: empty chamber.

Outside: Vel-1; Apple-A is not present/handled yet.

Door closes.

(09:00 power ON → cycle starts)

Instantaneous state at T_on1:

Inside (arrived): Apple-A with bruise already present.

(This is because Apple-A will be inside at T_off1 after the bruise is created.)

D1—09:05 (power ON)

Door opens (Vel-1).

Inside: Apple-A (bruised).

Vel-1 removes Apple-A.

Return obligation created: Apple-A must be back inside by 09:20.

Door closes.

Mark/bruise causal event—09:10 (not a door event)

Vel-1 drops Apple-A onto the bench edge.

This is the physical cause of the bruise on Apple-A’s worldline.

Why the bruise was already visible at 09:05

Because the apple that was visible at 09:05 is the same apple after the 09:10 drop, displaced back to T_on1 at 09:20.

Net: bruise cause is at 09:10, bruise observation is at 09:05 (bootstrap loop).

D2—09:15 (power ON)

Door opens (Vel-1).

Inside: empty (apple currently outside).

Vel-1 places Apple-A (bruised) back inside.

Return obligation satisfied conditional on it staying inside until T_off1.

Door closes.

(09:20 power OFF → displacement occurs)

At T_off1, Apple-A is inside, so it is displaced to T_on1.

D3—09:21 (power OFF)

Door opens (Vel-1 verification).

Inside: empty chamber (Apple-A is no longer at 09:21; it is now at 09:00).

Door closes.

Note-1 placement (non-time-traveled, bookkeeping only)

Vel-1 uses Note-1 as an external reminder: “Apple-A must be back inside by 09:20.”

Note-1 never enters the chamber in this micro-ledger.

(D) Consistency Audit Checklist (Prose Must Satisfy)

Every cycle must have explicit T_on and T_off, and the story must never treat the device as “always on” without redefining the cycle.

For each cycle: contents at T_off == arrivals at T_on, with matching identities (not just similar-looking objects).

Any arrived item removed from the chamber must be shown (or implied with certainty) to be back inside by T_off—no handwaving.

No scene may show someone inspecting the chamber and seeing it empty at time t, if the ledger requires an arrived item to already be inside at t.

The apple bruise must be consistent:

Visible when first removed in C1,

Physically caused at the logged moment,

Present earlier only because of the displacement at T_off1.

Temperature behavior must never drift into “fridge cooling” tropes:

Items keep their thermal state; no spontaneous chilling.

Any “cold” must come from items already cold before insertion.

Money/accounting must be closed:

Cash-2 and Cash-3 must originate from external counterparties (book, exchange, etc.), not from unreturned time-traveled cash.

If an object must be returned, it cannot be permanently “spent” or transferred away.

Duplicate-person scenes must respect overlap windows:

Vel-2 exists only during 13:00–19:00.

Vel-3 exists only during 19:30–23:30.

No post-T_off appearances of those copies unless a new cycle creates them.

Any written note that time-travels (Note-2/3/4) must have stable text history:

If it is updated during the overlap, the “arrived” version must already include those updates.

Failsafe causality must be clean:

Module-F1/Note-3 are returned by T_off3.

The installed protection that persists into C4 must be Module-F2 (the copy), not the arrived module.

No contradictory shutdown:

The prose cannot have Vel-1 “just unplug it” mid-cycle while an obligation item is still out, unless the plot explicitly shows the obligation being satisfied under the new earlier T_off.

The device’s role in each part must match the ledger:

Spoilage: discovery/verification.

Arbitrage: prediction → bet → winnings → note closure.

Compounding: safety bootstrapped → longer run → scaled profit → closure.

If you want, I can also add a one-page “object worldline diagram” (not prose) showing Apple-A / Note-2 / Note-4 as looped timelines with jump arrows, but the ledger above is already self-contained.

And then a story; the first version was obnoxiously formatted with nearly every sentence a paragraph, so I decided to intervene slightly to order GPT-5.2 Pro to fix that (the use of linebreaks here is extremely obnoxious. please fix the formatting to have more reasonable use of whitespace.). When I asked for a critique, it identified one logic error:

One concrete continuity flaw: the 19:00–19:25 segment double-books Vel‑1’s time unless you explicitly reorder or clarify what happened when.

First Story

Each fix is locally defensible and cumulatively fatal. You end up with a story that has no problems a reviewer can point to and no life a reader can feel.

Claude-4.6-opus (of this story)

The initial version:

Spoilage

We called them stasis fridges because the alternative was explaining a coil driver and a field geometry to people who wanted to know if their strawberries would last until Friday. It never cooled anything. If you put a cold six-pack inside, it stayed cold because it didn’t get a chance to warm up. If you put a hot burrito inside, it stayed hot because it didn’t get a chance to cool down. That was the pitch. Time was the insulation.

The prototype sat in the corner of Unit 12B between the parts racks and the folding table we used as a bench. A tall cabinet with a gasketed door and a latch that sounded too much like a freezer. Inside, it smelled like MDF, old silicone, and warm electronics. Room temperature, every time, unless you put something in already cold. The miswired unit happened because we were rushing. We’d swapped the driver board after a brownout and I’d re-terminated two bundles of coil leads at 2 a.m. under a headlamp. In the morning the field meter read “stable”, which was what we cared about.

The apple was supposed to be a clean demo. No cold air theatrics. Just: put it in, wait, take it out, show that it hadn’t browned. Enzymes don’t sell, but they’re honest. At 08:58 I killed my coffee and stared at the clock on my phone until it rolled over. I wrote on a Post-it and stuck it to the bench: NOTE-1: “Cycle test. Don’t improvise.”

At 08:59 I unlatched the door. The gasket peeled with a soft, sticky sound. Empty. Bare polymer racks, the little scratch I’d made with a screwdriver on the back wall, a strip of tape where we’d covered a seam. No apple. No prank. No object hidden in the corner. I ran my hand along the bottom, because I was tired and because tired makes you do rituals. Nothing. I shut it.

At 09:00 I hit the power strip. The driver fan came up with a dry whine. A relay clicked. The cabinet didn’t hum or glow or do anything cinematic. If you weren’t listening, you’d miss it.

I waited five minutes because five minutes was long enough for the field to stabilize, and because in a normal run you didn’t want to open the door right after power-on. We’d learned that the hard way when Mara—our only hire, our only adult—had yanked a lunch container out mid-field and complained her fork had felt “wrong”, like pushing through gel. I didn’t tell her about the miswire. I didn’t tell anyone anything.

At 09:05 I unlatched the door again. Same smell. Same stillness. But there was an apple on the middle rack. Green, slightly waxy, with a bruise on the side like someone had pressed a thumb too hard. I just stood there holding the door. My first thought wasn’t time travel. My first thought was that someone had been in the unit. My second thought was that the unit had been in someone else’s unit, in some other lab, and we’d gotten it mixed up.

Then the bruise resolved in my mind into detail. It wasn’t a thumb. It was an oval with a crescent notch, like a hard edge had caught it and then rolled away. I reached in and picked it up. Apple-A was room temp. Not even cool from sitting in plastic. Not warm either. Just… nothing had happened to it. My hands were warm; the apple didn’t steal heat. The cabinet didn’t give cold. It was a closet with a field on.

I set the apple on the bench and said out loud, to nobody, “This is new.” I glanced at NOTE-1 like it could argue back. There was a return obligation in the back of my mind already, even if I didn’t have words for it. The apple had been inside at 09:05 without me putting it there. The only way I didn’t go insane was by assuming it had come from some later moment. That meant whatever I did now had to complete a loop. It meant the apple had to go back.

I turned it slowly in my fingers, looking for stickers or ink. No sticker. No writing. Just the bruise. At 09:09 I took a photo with my phone, close enough that the bruise filled the frame.

At 09:10, fatigue did what fatigue does. I shifted my grip to rotate it and my thumb slid on the wax. Apple-A fell. It hit the bench edge exactly where a screw head was half proud because the cheap particleboard had stripped. A blunt thunk, more embarrassing than loud. I snatched it up like it was contraband.

The bruise was there. Still there. Same oval. Same crescent notch. The same mark I’d photographed a minute ago. I didn’t see it form. I couldn’t tell you, honestly, whether it deepened. But when I opened the photo and compared, the outline matched the screw like a template. The mark on the apple was a memory of an impact that, from the apple’s point of view, hadn’t happened yet. From mine, it had. From the cabinet’s, it was indifferent.

My mouth went dry. The room felt too bright. I looked at the screw head and then back at the apple and I had this impulse to cover the screw with tape, to refuse the bruise, to refuse the whole thing. But the bruise was already in my hand. If I refused it, it would still be there. That was the worst part.

I checked the clock again. 09:12. I had eight minutes to put the apple back. Nine if I wanted to flirt with rounding error. I cleaned the bench edge with my sleeve, not because it mattered, but because I needed to do something.

At 09:15 I opened the cabinet. Empty. Of course it was empty; the apple was in my hand. I placed Apple-A on the rack in the same orientation it had been when I’d found it, bruise facing out like an accusation. Then I pulled my hand back fast, like the cabinet might bite. I latched the door. The fan kept whining. I stared at the latch. I didn’t touch it again.

At 09:20, exactly, I cut power at the strip. The fan coasted down. The relay clicked the other way. The cabinet became a normal cabinet again, which was to say: a box. At 09:21 I opened it. Empty. No apple. No mark. No proof except the photo and the bruise in my head. I closed it gently. My hands were shaking, but not from adrenaline. From lack of sleep. From realizing that if I was right, I had just met the edge of a thing we were not funded to understand.

I found a dry erase marker and went to the board by the roll-up door where we tracked inventory and burn rate and the delivery schedule we were already missing. On the whiteboard I drew a straight line labeled “09:00 → 09:20” and a bent arrow that jumped back from the right end to the left. I wrote “Apple-A (bruise)” at the bend. Under it, I wrote, smaller, “Door open 09:05 (remove) / 09:15 (return).” Then I circled “09:20” like circling it would hold it in place. The board looked stupidly simple.

The cabinet didn’t. The field meter was still sitting on the bench where I’d left it, reading stable, as if stable was a moral position. My phone buzzed with a calendar reminder for a call with an investor at 10:00. I stared at it until it went quiet.

The apple loop had been a closed circle with no beginning. The bruise existed because it had to. And if an apple could do it, then information could do it, and if information could do it, then our runway could do it. That thought arrived with the same dull inevitability as the apple had. I didn’t say it out loud. I wrote a second Post-it and stuck it under NOTE-1. “Don’t tell Mara.” Then I went back to the cabinet and started planning a longer cycle.

Arbitrage

A timebox isn’t useful until you can carry something out of it. An apple is proof. A note is leverage. A person is a liability.

I didn’t have a partner in Unit 12B in the way people mean. Mara was payroll and safety glasses. Our lawyer was an email thread. The cabinet was mine because I was the one who slept on the floor next to it. So if I wanted a person to carry something out, I had to use myself.

I started numbering. Not because it made it less insane, but because it made it easier to not make a mistake. Vel-1 was me, the one who would keep going no matter how many loops we made. Vel-2 would be the copy who came out of the cabinet at the start of the next cycle and went back in at the end. That was the rule the apple had taught me. If it came out, it had to go back.

At 12:40 I pulled the rolling chair up to the bench and wrote a checklist in my notebook. Power-on: 13:00. Power-off: 19:00. Do not be at the door at 13:00–13:05. Do not interrupt power. Do not bring extra objects into the cabinet at 19:00.

I set an old webcam on the shelf facing the cabinet door. No cloud. No account. Just an SD card because I didn’t want a subpoena to find me by accident. I left an envelope in the top drawer of the bench with CASH-1 written on it in block letters. Three hundred in twenties. Not a lot of money. Enough to make a bet without looking like a joke. Enough to matter to me.

At 12:55 I checked the cabinet with the same ritual as the apple run. Door open. Empty. Door shut. Latch. I stood with my hand on the power strip and breathed until my pulse stopped trying to climb out of my throat. The thing about doing it on purpose is that your brain doesn’t give you the mercy of disbelief.

At 13:00 I flipped the switch. Fan. Relay. No cinematic anything. I didn’t look at the door. I walked away like it was a microwave. I went out into the little yard behind the unit and stood between the dumpsters where no one could see me through the front window. I watched the clock change on my phone. 13:01. 13:02. I could hear the faintest change in sound through the wall when the latch moved. Metal on metal. The cabinet opening.

My mouth filled with saliva like I was about to vomit. I stayed by the dumpsters. At 13:05 I went back inside and forced myself to do normal things. Answer a Slack message. Move a box of injection-molded trays from one shelf to another. Make tea because my hands needed something warm that wasn’t coffee. If Vel-2 existed, he would already be gone. If he wasn’t, then the whole thing was a fantasy and I could go back to pretending I was building a product.

At 14:00 Mara texted that she was running late because her train had stopped “for police activity.” I typed back “OK” and then deleted it and typed “OK” again, because I couldn’t remember if my first “OK” had gone through. That’s what the cabinet did to my brain. It made every trivial thing feel like a hinge.

At 18:55 I was back in Unit 12B. Not at the cabinet. Near the power strip, because the only promise I could keep was the off-time. The fan had been whining for almost six hours. Heat from the driver board had warmed the air in the cabinet a few degrees, but the cabinet itself didn’t breathe. It didn’t exchange. Nothing about it felt like a fridge. It felt like a lie we’d wrapped in a door.

I watched the webcam’s little status LED and listened. At 18:58 the latch clicked. Footsteps. Breathing. A soft grunt like someone moving carefully. I didn’t turn. I stared at the power strip like it was a detonator. The sound of paper sliding on plastic. A pause. Another breath. Then, quieter, the squeak of the rack as weight shifted. Vel-2 climbing in. At 18:59 the latch clicked again. The cabinet was closed.

At 19:00 I killed power. Relay. Fan dying. Silence. I waited a full minute before I moved. The minute was for superstition, not physics. At 19:01 I opened the cabinet. Empty. No person. No note. No evidence that any of the sounds I’d heard had been real.

In the top drawer, under the solder spool, was a second envelope. CASH-2 in my own handwriting. Thicker. I didn’t open it right away. I sat on the floor with my back against the cabinet and stared at it until my eyes hurt. When I finally tore it open, it was cash, warm from being in a drawer all day. A lot more than three hundred. There was also a folded betting slip—BetSlip-1—printed on glossy paper with a timestamp at 13:16. The kind you get from a kiosk when you don’t want a digital trail. I’d never touched it.

Next to it was a plain piece of paper torn from my notebook, not time-traveled because it wasn’t inside the cabinet at any power-off, just left like any other thing you leave for yourself when you don’t trust yourself. Three lines. “Placed 13:15 with Cash-1.” “Game ended 18:40. Note matched.” “Cashed 18:55. Left you Cash-2. Don’t come to door.” No signature. But the pen pressure was mine. The phrasing was mine. The sting of recognition was physical.

I watched the webcam footage on my laptop with the volume off. At 13:02 the cabinet door opened. Vel-2 stepped out. Same hoodie. Same half-grown beard. Same posture of someone who’d slept badly. He held a small folded paper—Note-2—and he didn’t look at the camera. He went straight to the drawer, took the CASH-1 envelope, and left. At 18:59 he came back. He looked thinner. He put Note-2 into the cabinet, climbed in, and shut the door behind him.

It was exactly as clinical as the apple. No drama. No warning. Just a human being treating himself like an object that needed to be returned by a deadline.

I didn’t keep the footage on the laptop. I copied it to a thumb drive and hid it in the ceiling tile above the bathroom because paranoia is a kind of maintenance. Then I took the marker to the board by the roll-up door again and drew another simple diagram that felt like an insult to how sick I was. On the whiteboard I wrote “13:00 ON / 19:00 OFF” and sketched a box in the middle. I drew two stick figures: “Vel-1” on the outside line and “Vel-2” as a loop that started at 19:00, jumped back, and ended at 19:00 again. I wrote “Note-2” next to it. I underlined “Return obligation” twice. When I capped the marker, my hand cramped.

I thought about how we were supposed to be building a consumer appliance. How we’d fought about door hinges and gasket suppliers and whether the UI should be a touch panel or a knob because “people like knobs.” Now I had a cabinet that could print money by rewriting causality, and the only thing keeping it from burning down our unit was a cheap power strip and my ability to not blink at the wrong time.

Mara texted again at 19:10. “Still here?” I typed “yeah” and then I deleted it. I didn’t want my phone to be a record of anything. Instead I put it face down and went back to the cabinet. If I was going to keep doing this, I needed a way to survive it. Not morally. Electrically.

Compounding

The danger wasn’t paradox. The danger was a breaker tripping in the middle of a cycle. A landlord flipping the wrong switch. A driver board overheating and crowbarring itself. If power-off defined the end of the cycle, then an accidental power-off redefined it, and anything you’d taken out would still owe you a return you could no longer pay. That was how you died. Not with a grandfather. With a missed deadline.

At 19:03 I rearranged the bench like I was prepping for surgery. Soldering iron in its stand. Multimeter leads untangled. A tray of components pulled from stock: relays, thermistors, a little microcontroller we used for the normal stasis mode timing. A clean notebook page ready for whatever came out of the cabinet.

At 19:05 I powered on. Fan. Relay. My skin had learned the sound and reacted before my mind did. At 19:06 I opened the door. The cabinet held a small circuit board in an anti-static bag and a folded sheet of paper. Module-F1 and Note-3, sitting on the middle rack like they’d always been there. I didn’t touch them for a full second. My brain tried to find an origin story. A courier. Mara. A forgotten shipment. But the apple had burned that reflex out. If it was inside at 19:25, it was here now. And if I took it out, it had to be back in by 19:25.

I grabbed the anti-static bag and the folded paper and shut the door. On the bench I opened Note-3 first. It was a wiring diagram in my own shorthand. Pin labels I used when I didn’t want to think. A threshold value circled three times. A test procedure: “Heat sensor to 60℃; verify LIMIT, not OFF.” That line mattered. A failsafe that cut power would kill the cycle. A failsafe that limited the driver while keeping the cabinet logically “on” would keep the worldline intact. Module-F1 in the bag looked like exactly that. A current limiter with a thermal input and a latching relay that bypassed the limiter only at startup. It was the kind of board I would’ve designed if I’d had time. I didn’t have time. I had nineteen minutes.

From 19:07 to 19:18 I worked with the frantic calm you get when you’ve accepted that the deadline isn’t negotiable. I traced Module-F1’s layout, checked the BOM scribbled on the back of Note-3, and pulled parts from our bins. I wasn’t building something elegant. I was building something identical enough that it would function. Module-F2 was a copy with slightly uglier solder joints.

At 19:18 I cut power to the driver board only—leaving the cabinet powered and the cycle running—by flipping the service toggle we used for maintenance. The fan stayed on. The relay in the cabinet stayed engaged. The cycle’s “on” state stayed true. Then I spliced Module-F2 inline on the coil feed. At 19:22 it was installed.

At 19:23 I clipped a heat gun to the bench vise and aimed it at the thermistor. I watched the multimeter and the LED on Module-F2. At 60℃ the LED changed. The driver current dropped. The fan kept running. The cabinet stayed on. No relay click. No power-off. That was what Note-3 had promised. That was what Module-F1 must have been built to ensure. I turned off the heat gun and let my lungs remember how to breathe.

At 19:24 I opened the cabinet and returned Module-F1 and Note-3 to the rack. I positioned them exactly as I’d found them, because I’d learned to respect stupid details. Door shut. Latch. At 19:25 I powered off the cabinet. Fan dying. Relay click. Silence. At 19:26 I opened the cabinet. Empty. The originals were gone, displaced back to 19:05, waiting to be taken out by the version of me who’d be there at 19:06. Bootstrap doesn’t feel like magic when you’re holding a soldering iron. It feels like theft.

At 19:27 I took CASH-2 from the envelope Vel-2 had left and counted it twice. Then I put it in a new envelope and wrote “For Vel-3” on it, and I put it in the top drawer where Vel-2 had found Cash-1. I didn’t like writing that. I didn’t like that there was now a Vel-3. But the cabinet didn’t care about what I liked.

The long cycle had to start at 19:30 if we wanted a full evening window. That gave me three minutes to become the kind of person who could do this twice in one day. At 19:30 I powered on again. Fan. Relay. The cabinet was back in its indifferent state. I stayed away from the door. Not out of superstition, but out of strategy. If Vel-3 existed, he would come out at 19:31 with whatever Note-4 told him to do. If he saw me, he might talk. If he talked, I might answer. If I answered, I might say something I couldn’t unsay.

At 19:31, from across the unit, I heard the latch. A soft click. A pause. The door opening. Footsteps. The drawer sliding. The envelope rustling. Then the cabinet door shutting again. Vel-3 leaving. I didn’t move until 19:35. When I finally went near the cabinet, it was latched and humming quietly with the fan. Nothing to see. Just a powered box.

The rest of the evening was waiting. Module-F2 sat on the coil feed with its LED steady. I watched it the way you watch a sleeping animal you don’t trust. I didn’t touch my phone. I didn’t open the cabinet. I worked on normal things. Wrote an email draft to the manufacturer about gasket tolerances. Updated a spreadsheet with shipping costs. Anything to keep my hands from drifting back toward the cabinet like a nervous tic.

At 22:50 I heard the roll-up door at the front of the unit rattle. Not open. Just a vibration, like someone had leaned on it. A reminder that the world still existed outside the loop.

At 23:10 there was a soft knock on the side door from the alley. Three taps, spaced evenly. I froze. Then I realized, with a nausea that felt like hunger, that the knock wasn’t asking to be let in. It was a signal. I waited a full minute and then cracked the side door. No one. Just the smell of asphalt and the hum of the freeway. On the ground, tucked against the threshold, was a small lockbox we used for petty cash. It hadn’t been there an hour ago. The lid wasn’t locked. Inside was an envelope: CASH-3. And a page torn from my notebook with a single line and a set of numbers. “Code’s in your book. Don’t look up until after.”

I went back inside and sat at the bench, staring at my own notebook like it was radioactive. In the margin of today’s page, in handwriting that was mine but slightly slanted, a sequence: “23:10—4-9-2.” Under it: “If you’re reading this, you made it clean. If you keep going, don’t pretend it’s still about food.” That was all. No explanation of the trades. No confession. Just the moral weight dropped like a tool onto a table.

At 23:25 I took my place by the power strip again. The cabinet still hummed. Module-F2’s LED stayed steady. At 23:28 the latch clicked. Vel-3 was back. I didn’t turn. Paper sliding on plastic. A breath. A grunt as weight shifted. Vel-3 climbing into the cabinet. At 23:30 I killed power. Relay. Fan dying. Silence. And then, as always, the sense that something fundamental had happened in a place my senses couldn’t reach.

At 23:31 I opened the cabinet. Empty. No Vel. No Note-4. No proof. Just a warm plastic rack and the smell of the unit. I latched it again and leaned my forehead against the door. My reflection in the dark plastic looked like somebody else’s face.

CASH-3 sat on the bench in front of me, more money than we’d ever had that wasn’t debt. I didn’t open it. I didn’t need to. Money is money. The part that mattered was the sentence in my notebook. If you keep going, don’t pretend it’s still about food.

I walked to the board by the roll-up door for the last time that night, because my brain needed to see it in lines and arrows instead of in my bloodstream. On the whiteboard I drew the cabinet as a square and wrote “19:30 ON → 23:30 OFF” above it. I added a small box labeled “Module-F2 (LIMIT, not OFF)” on the power line. I drew Vel-3 as a loop that left at 19:31 and returned at 23:28 with “Note-4” and then jumped back at 23:30. Off to the side I wrote “Cash stays out” and underlined it. Then I capped the marker and stared at the diagram until it stopped making sense.

My phone buzzed, face down. A call. Mara. I let it ring out. A second buzz. A text. “QA found something. One of the production units holds temp even when unplugged. Like… too well. Can you look tomorrow before we ship?”

I read it twice. Holds temp even when unplugged. A unit that stayed “on” without power, in the only way the cabinet ever cared about. I thought about customers putting hot soup inside and walking away. I thought about a child opening a door and taking something out that had “arrived”, not knowing it owed itself back by a deadline. I thought about a world full of cabinets making obligations nobody understood.

CASH-3 sat on the bench. The cabinet sat in the corner, quiet, innocent, empty. The sentence in my notebook didn’t tell me to stop. It didn’t tell me to continue. It just stripped the cover story off.

I typed a reply to Mara. “Don’t ship. Tell them a fuse issue. I’ll be in early.” My thumb hovered over send. Behind my eyes, the cabinet’s simple rule pulsed like a metronome: anything you take out, you have to put back. I looked at the power strip. I looked at the time. I looked at the cabinet door and imagined opening it at some future T_on to find not an apple, not a note, not a copy of myself, but someone else. Someone who hadn’t agreed. Someone whose obligation would be mine the moment I touched the latch. I didn’t hit send. I didn’t not hit send. I just sat there until the phone went dark again, and the only sound in Unit 12B was the faint ticking of a cheap wall clock, counting down toward whatever I’d already decided to do.

I then began running this through the usual gauntlet of iterative editing prompts, using not just GPT/Claude but Gemini-3-pro-preview, Kimi K2.5 Thinking, and DeepSeek-v3 for kicks. The “Poetry magazine” prompt was revised to be a “Clarkesworld Magazine” prompt (leading to the amusing issue that the LLMs would sometimes warn that Clarke’s World has strictly banned AI-related submissions and to be sure that this story wasn’t AI-written in any way). I avoided doing any curation or feedback on the content, and tried to confine myself to simply copy-pasting critiques and suggestions back and forth, using GPT-5.2 Pro as the master session. (I would have used Claude more to test it out, but the usage quota for Claude-4.6-opus on maximum thinking settings is low.)

An example:

…Report:

I’ll review this science fiction story for you. This is a substantial piece, so let me analyze it thoroughly.

Summary

“Spoilage” is a hard science fiction story about a startup that accidentally invents time travel while building “stasis fridges”—devices that preserve food not by cooling it, but by stopping time inside them. The narrator, an engineer at a failing startup, discovers that a miswired prototype creates closed timelike curves: objects placed inside during the “off” state can be retrieved from the “on” state, but must be returned before power-down or reality enforces the balance with lethal consequences. When production units inherit the same dangerous property—remaining “logically ON” even when unplugged—the narrator and his colleague Mara must stop a shipment before customers start disappearing into temporal debt collection.

Analysis

Strengths

Engineering Authenticity The story excels at technical verisimilitude. The narrator’s voice is pure exhausted startup engineer—jargon-heavy, ethically compromised, sleep-deprived. Details like “conformal-coated,” “fiducial,” “brownout handling,” and the specific horror of “eleven weeks from payroll insolvency” ground the fantastic element in mundane reality. The prose treats time travel as a bug, not a feature, which is refreshing.

Conceptual Rigour The time mechanics are internally consistent and genuinely interesting. The “bookkeeping” metaphor—“no net change across a cycle”—extends naturally to personal stakes: “IF OUT → MUST RETURN.” The horror isn’t paradox (grandfather killed) but accounting (debt collection). The quarter “half-sunk into the polymer rack” and the badge fused into the shelf are visceral images of space-time’s indifferent reconciliation.

Structural Control The three-act structure (Spoilage/Arbitrage/Compounding) mirrors both financial terminology and escalating personal investment. Each section builds logically: discovery of the effect → exploitation for engineering solutions → catastrophic realization of commercial scale. The pacing accelerates appropriately.

Character Work Mara emerges effectively from minimal brushstrokes—“payroll and safety glasses and the only one of us who remembered to eat lunch on purpose.” Her arc from colleague to accomplice to moral anchor works. The narrator’s self-loathing is palpable: “the small, ugly thing because small, ugly things are easier than big confessions.”

Weaknesses

Prose Density The technical precision sometimes suffocates emotional beats. Sentences like “The controller never wanted to see a hard OFF during a run. It dithered, throttled, blinked coil current—anything but admit the field had stopped” are strong, but the story rarely lets itself breathe. The narrator’s exhaustion is told through sleep deprivation references but rarely shown through altered perception or physical deterioration beyond shaking hands.

The Bootstrap Paradox The Module-F1/F2 sequence, while clever, relies on unexamined bootstrap paradox mechanics. Where did the original Module-F1 come from? The story gestures at “theft of origin” but doesn’t grapple with the ontological weirdness of information without source. This is forgivable in a short piece, but the narrator’s lack of curiosity here feels convenient rather than character-driven.

Mara’s Conversion Her acceptance of the impossible happens too easily. After the badge demonstration, she shifts from skeptic to accomplice with minimal resistance. The line “That is not a sentence a sane person says about a refrigerator” is strong, but her subsequent collaboration feels engineered for plot momentum rather than psychological truth. A moment of genuine rejection or escape attempt would strengthen the final act.

The Ending The story stops rather than concludes. “DEFAULT” circled on the whiteboard is a strong final image, but the stakes remain abstract. We don’t see the consequences of the quarantine—regulatory, financial, existential. The narrator’s arc completes (he acts responsibly), but the narrative promise of “a deadline was moving toward us” remains unfulfilled. This may be intentional (horror of the unknown), but it reads slightly unfinished.

Critical Assessment

Theme: The story explores technological ethics through the lens of startup culture’s “move fast and break things” mentality. The fridge becomes a metaphor for technical debt—problems deferred until they become catastrophes. The “bookkeeping” motif suggests capitalism’s tendency to abstract human cost into accounting entries.

Genre Positioning: This is “hard SF horror” in the tradition of Greg Egan or early Chiang, though less philosophically ambitious than the latter. The horror is cosmic indifference filtered through OSHA violations and supply chain logistics.

Market Fit for Clarkesworld: Strong. The magazine publishes technically rigorous SF with literary sensibilities. The story’s length (approximately 7,500 words) is appropriate. The engineering perspective and economic anxiety align with contemporary SF trends.

Recommendation

ACCEPT with minor revisions or ACCEPT as-is

The story’s conceptual strength and technical execution outweigh its structural issues. For improvement, consider:

Mara’s skepticism: Extend her resistance through one more beat—perhaps she leaves, then returns with evidence that forces her belief.

The ending: Either commit to the abrupt stop (horror of incompleteness) or add 200-300 words showing the immediate aftermath—regulators arriving, the narrator’s first night knowing he’s created something that can’t be uncreated.

Sensory texture: One scene of genuine hallucination or perceptual distortion would validate the narrator’s exhaustion more effectively than repeated references to sleep deprivation.

The core image—the quarter half-sunk in plastic, the badge fused into the shelf—is indelible. The story understands that the most disturbing time travel is not adventure but accounting, and that the universe’s indifference to human meaning is scarier than any monster. This is accomplished, disturbing work that deserves publication.

Our reviewers recommended revise-and-resubmit. To help the author, please write out a detailed peer review report of the story; start at the global level and work your way down to the line level, with detailed suggestions. If suggesting a change, try to consider at least 3 options for each change.

[after including several reviews]

Story Summary

A startup engineer builds “stasis fridges” that don’t cool—time is the insulation.

The product spec guarantees “no net change across a cycle”, and the firmware tries hard to avoid an actual OFF event.

After minor anomalies (a fork feeling like it’s pushing through gel; a quarter half-embedded into a polymer shelf after a power sag), a miswired dev unit produces the first clean proof: an apple appears mid-cycle already bruised in the exact shape of a screw it hasn’t hit yet.

The engineer realizes the cabinet is enforcing endpoint consistency, not preventing events.

If something is “inside” at OFF, it must have been inside during ON; if something is removed, it must be returned—or the interval will reconcile the books some other way.

To get leverage and control, he deliberately creates a timeboxed “Two”: a future/past version of himself who can step out near the beginning and return near the end.

Two brings back critical information about production boards: “unplugged” does not mean OFF, and a door-sensor failsafe can force a hidden OFF that closes the ledger on its own schedule.

The engineer uses a bootstrap loop (a module that appears, is copied, and is sent back) to regain control of OFF-like behavior and reduce accidental sag deaths.

Then Mara arrives with a boxed production unit from QA—one that won’t die when unplugged.

On the “third open”, it forces a hard end, and the reconciliation produces horror: a contract manufacturer’s badge appears and then embeds itself into the rack like the quarter.

The implication is human-scale: someone’s labor—and possibly their body—was used as substitute collateral when a loop didn’t get paid back.

They try to halt shipments, knowing the only safe “default” is never letting these units decide OFF for themselves.

The last image is a ticking clock and a product that will eventually reconcile its debts in someone’s kitchen.

Analysis of What’s Already Strong and What’s Unstable

What’s Already Working

Voice and texture. The exhausted engineer POV is consistent, competent, and concrete.

Procedural horror. The dread comes from checklists, firmware behaviors, and power events, not from spectacle.

Core rule is generative. “No net change across a cycle” turning into literal endpoint enforcement is elegant and unusually fresh.

Anchor images. The quarter embedded “perfectly level” is a perfect physical impossibility.

What Currently Destabilizes the Read (And Why Reviewers Converged)

Two conceptual engines are adjacent but not causally fused. The bootstrap module scene reads like clever SF; the badge reads like cosmic debt collection.

The story wants those to be the same phenomenon (borrowing causes interest), but it currently feels like “we did a neat paradox” and then “separately, horror.”

OFF vocabulary is doing too much work. You have at least three OFFs (mains removal, coil current drop, controller state transition), plus “door defines inside.”

If a reader gets even slightly lost here, tension bleeds away because the fear is “I can accidentally close the ledger”, and that requires crisp boundaries.

Mara’s turn is too fast. She’s effective as pressure and conscience, but she needs one more beat of refusal/skepticism/agency so the final alliance is earned rather than convenient.

Hard-SF reader snag: temporary duplication mass/energy. If Two exists outside for hours, something should “pay” (power draw, instability, exchange, or a stated violation that becomes part of the horror).

Right now, the story’s own metaphor says “bookkeeping”, so readers expect to see the bill.

Ending commitment. “DEFAULT” is a good poetic stop, but reviewers are right that you need one extra concrete commitment or consequence so the ending lands as tragedy, not “near miss.”

Reviewer Suggestions Ranked by Usefulness

Rank

Suggestion (compressed)

Why it’s high leverage

Sources

1

Standardize ON/OFF terms (define “hard OFF” that closes the books; separate from unplug/coil)

Clarifies the governing rule; prevents confusion from stealing dread

R1, R2, Final

2

Integrate bootstrap with debt collection (bootstrap is borrowing; interest is instability/harm; ending becomes inevitable)

Turns “two cool ideas” into one engine; makes climax feel earned

R1, Final

3

Give Two a visible cost (power draw, bodily instability, marks, or ethically compromising specifics)

Pays the physics bill; deepens horror; makes “arbitrage” feel like theft

R2, R1, Final

4

Earn Mara’s conversion / agency (skepticism + refusal beat + decisive action)

Fixes the biggest character pacing complaint; raises stakes via conflict

R1, R2, R3, Final

5

Seed cross-unit coupling early (shared QA sync frame / phase-lock)

Makes badge escalation rule-driven rather than twisty

Final

6

Slow and humanize the badge moment (name/photo/rocket; breathing room; connect to quarter/gel)

Gives the climax human weight; makes the “victim” real

R1, R2, R3, Final

7

Make the resolution harder / more costly (distributor pushback; explicit payroll/company sacrifice; external report)

Upgrades ending from “responsible step” to “irreversible choice”

R1, R2, Final

8

Clarify the apple bruise geometry

Removes a key visualization snag in the first proof

R1

9

Motif management (corrupt repetitions; vary refrains)

Polishes voice and keeps repetition from feeling mannered

R1, Final

10

Line-level clarity tweaks (“blink coil current”, syntax simplifications)

Worth doing, but subordinate to rule/character/ending fixes

R1, R2, R3

Below is a revision that implements the top items without changing the story’s identity: same procedural dread, same timestamps, but tighter rule vocabulary, clearer physics “billing”, stronger Mara agency, explicit cross-unit seeding, and an ending that costs something. …

Rank	Suggestion (compressed)	Why it’s high leverage	Sources
1	Standardize ON/OFF terms (define “hard OFF” that closes the books; separate from unplug/coil)	Clarifies the governing rule; prevents confusion from stealing dread	R1, R2, Final
2	Integrate bootstrap with debt collection (bootstrap is borrowing; interest is instability/harm; ending becomes inevitable)	Turns “two cool ideas” into one engine; makes climax feel earned	R1, Final
3	Give Two a visible cost (power draw, bodily instability, marks, or ethically compromising specifics)	Pays the physics bill; deepens horror; makes “arbitrage” feel like theft	R2, R1, Final
4	Earn Mara’s conversion / agency (skepticism + refusal beat + decisive action)	Fixes the biggest character pacing complaint; raises stakes via conflict	R1, R2, R3, Final
5	Seed cross-unit coupling early (shared QA sync frame / phase-lock)	Makes badge escalation rule-driven rather than twisty	Final
6	Slow and humanize the badge moment (name/photo/rocket; breathing room; connect to quarter/gel)	Gives the climax human weight; makes the “victim” real	R1, R2, R3, Final
7	Make the resolution harder / more costly (distributor pushback; explicit payroll/company sacrifice; external report)	Upgrades ending from “responsible step” to “irreversible choice”	R1, R2, Final
8	Clarify the apple bruise geometry	Removes a key visualization snag in the first proof	R1
9	Motif management (corrupt repetitions; vary refrains)	Polishes voice and keeps repetition from feeling mannered	R1, Final
10	Line-level clarity tweaks (“blink coil current”, syntax simplifications)	Worth doing, but subordinate to rule/character/ending fixes	R1, R2, R3

The final version was terrible; possibly millions of tokens, wasted to simply spoil a workable first draft:

Spoilage

We called them stasis fridges because the alternative was explaining a coil driver and field geometry to people who wanted to know if their strawberries would last until Friday. It never cooled anything; if you put a hot burrito inside, it stayed hot because it didn’t get a chance to cool down. Time was the insulation. That wasn’t a miracle. It was the kind of trick you can sell with a warranty clause.

In the shipping spec, “stasis” meant no net change across a cycle—not “nothing happens”, just “the totals match at the endpoints.” We pretended OFF was a single word until it started showing up as different events in failure reports, depending on whether you meant the wall power, the coils, or the controller admitting the run was over. The controller never wanted to see that last one during a run. It dithered, throttled, stuttered the coil current in millisecond bursts—anything but register the field’s collapse. If you asked me what the field did to you while it was on, I’d have said “nothing” with a straight face.

Then Mara pulled her lunch container out too fast and said her fork felt wrong, like pushing through uncured epoxy with grain. Afterward the fork’s tines weren’t quite parallel—maybe a millimeter out at the tips, a twist you’d expect from torque, not from bending. We blamed cheap plastic and stress and not sleeping, and went back to work because that’s what you do when payroll is a countdown clock.

A week later, during an overnight soak test, the building breaker hiccuped. Not a clean OFF—just a sag, a blink—the kind of thing a decent board should ride through. It didn’t.

We kept a quarter on the middle rack as a dumb fiducial—something you can point at when you’re arguing whether a graph is noise. After the blink it was half-sunk into the polymer rack, face up, perfectly level, like the plastic had yielded around it and then decided it had always been that way. The reeded edge vanished into the rack teeth in a clean line: no melt, no seam, just an interface that shouldn’t exist.

We took photos, bagged the rack, wrote POWER SAG / DRIVER GLITCH on the label because labels are cheaper than conclusions. Then we told ourselves production wouldn’t ever see that failure mode because production had a clean driver revision and proper brownout handling, and because we needed there to be a line between the dev mule and what we were about to ship.

Production also had a “feature” we’d been proud of on a slide deck: a latching regulator and a fat hold-up bank so the logic wouldn’t brown out when someone yanked a cord and jammed it back in. Faster reboot, better logs, fewer angry emails; Mara had championed that slide, back when “resilience” was the closest thing we had to virtue. And because QA hated drift, production units listened for a reference pulse during calibration—phase-lock, fleet sync, whatever name you put on it when you don’t want to say “shared frame.” Cleaner graphs, less privacy than we assumed.

That was also when I added the keyed service toggle on the driver panel: you could cut coil current without the controller logging the event it treated as a cycle end. Officially it was for safety. Unofficially it was so you could work inside the machine without the firmware declaring the run was over.

The dev mule sat in Unit 12B between the parts racks and the folding table we used as a bench. In there, the cabinet smelled like MDF, old silicone, and warm dust on heatsinks, and the gasket peeled with that soft, sticky freezer sound when you unlatched it. If you crouched you could see a tiny logic LED through the vent slots—green when the controller still believed it was running, dark when it had finally admitted OFF. After the quarter incident I’d kludged in two supercaps and a diode so the logic could ride a blink without losing state; when you cut mains on purpose, they drained in seconds. Enough to make “momentary” mean something. Not enough to hide a shutdown from you if you were watching.

The miswired unit happened because we were rushing. We’d swapped the driver board after a brownout and I’d re-terminated two bundles of coil leads at 2 a.m. under a headlamp, and in the morning the field meter read stable, which was what we cared about. Stable, as if stable were a moral position.

The apple was supposed to be a clean demo. No cold air theatrics; just put it in, wait, take it out, show it hadn’t browned. Enzymes don’t sell, but they’re honest.

At 08:58 I drained my coffee and stared at the clock on my phone until it rolled over. I wrote on a Post-it and stuck it to the bench: NOTE-1: Cycle test. Don’t improvise. At 08:59 I unlatched the door. Empty.

At 09:00 I hit the power strip. The driver fan came up with a dry whine and a relay clicked—no glow, no hum, nothing cinematic—and if you weren’t listening you’d miss it. At 09:05 I unlatched the door again. Same smell, same stillness, but there was an apple on the middle rack: green, slightly waxy, room temperature in the way only untouched things are, as if it hadn’t exchanged heat with anything since whenever it had last been real. A bruise sat on one side like someone had pressed a thumb too hard.

I just stood there holding the door. My first thought wasn’t time travel; my first thought was that someone had been in the unit. The bruise was obvious, but what took a second was its geometry: not a smear, not a soft dent, a crescent bite out of an oval, concave side down, like the apple had kissed a curved edge and then rolled.

I picked it up and my eyes snagged on a screw head half-proud at the bench edge where the cheap particleboard had stripped. The torn Phillips slot had a burr—a little crescent of raised metal where the driver had chewed it—and the bruise on the apple was the same curve. Not “kind of”, not “close enough”: same radius, same orientation, like the apple had been stamped with that screw’s damage.

I set the apple down and said out loud, to nobody, “This is new.” I glanced at NOTE-1 like it could argue back, and what came next wasn’t a theory so much as the only assumption that kept my brain from snapping. The miswire hadn’t made the effect stronger. It had made the interval closed. Before, ON-to-OFF was a line; now it was a loop, and the controller was enforcing the endpoints as hard boundaries. The apple wasn’t a gift; it was a balancing entry.

At 09:09 I took a photo with my phone, close enough that the bruise filled the frame. At 09:10 I grabbed a strip of tape and covered the screw, trying to deny the bruise its cause, and the tape stuck to my thumb the way tape always does when you need it not to. The apple shifted in my other hand—wax on skin, a slide—and then a blunt thunk as it kissed the screw anyway, exactly where the bruise said it would. It wasn’t loud; it was definitive.

I snatched it up and turned it over like there was some other explanation hiding on the far side. The bruise was still there, same oval, same crescent bite, and when I opened the photo and compared the outline matched within the thickness of my hand shaking. The bruise wasn’t a prediction; it was a receipt.

At 09:15 I opened the cabinet. Empty, of course, because the apple was in my hand. I placed it on the rack in the same orientation it had been when I’d found it, bruise facing out like an accusation, and pulled my hand back fast like the cabinet might bite.

At 09:20 I cut mains at the strip. The fan coasted down, and through the vent I watched the little green logic LED fade and die a second later. That was the controller admitting it: hard OFF. At 09:21 I opened the door. Empty. No apple, no proof except the photo and the bruise in my head, and the creeping sense that the quarter in the rack hadn’t been “damage” so much as the universe reconciling a mismatch with whatever compliance it could borrow.

On the whiteboard by the roll-up door I drew a straight line labeled 09:00 → 09:20 and a bent arrow that jumped back from the right end to the left. I wrote Apple-A at the bend and under it: Door open 09:05 (remove) / 09:15 (return). Then I wrote three labels beside the line because I could feel language failing: MAINS OFF. COIL OFF. HARD OFF (books close). Marketing pretended those were synonyms, and I circled HARD OFF until the marker squeaked.

My phone buzzed with a calendar reminder for an investor call at 10:00. I didn’t take it. At 10:15 it buzzed again—voicemail—and I watched it go quiet because answering would have required words like “apple” and “ledger” and “no”, and I didn’t have any of those ready.

From 09:30 to noon I tried to disprove myself without giving the cabinet another clean loop to bite into. I checked wiring twice, traced coil bundles, re-labeled what I’d already labeled, and stared into the empty racks until my eyes watered. I kept thinking about the quarter and the fork and the fact that a human body had a lot more coordinates than a quarter, and a lot more to lose if the books ever closed without a way to pay.

I wrote a second Post-it and stuck it under NOTE-1: Don’t tell Mara until you can define HARD OFF. Then I sat on the rolling chair and looked at the cabinet like it was a problem set with a deadline. If I was going to test this at human scale, I needed help I didn’t have, so I decided to borrow it from myself.

Arbitrage

A timebox isn’t useful until you can carry something out of it. An apple is proof, but a person is leverage because a person can do work, and that was the first honest thought I had and I hated myself for how quickly it felt like engineering.

I started numbering in my notebook the way you number versions when you don’t trust memory. One was me: the operator, the one who stayed on the outside line. Two would be the me whose worldline kinked through the cabinet—out near the beginning only because he would climb back in near the end—and from Two’s perspective there was no after, only return.

I wrote a rule in block caps: IF OUT → MUST RETURN. My hand hovered over the paper longer than it should’ve, and a wave of nausea came up like my body had understood the rule before my brain had.

At 12:40 I wrote a checklist. Power-on: 13:00. Hard OFF: 19:00. Do not be at the door at 13:00–13:05. Do not interrupt power. Service toggle only if you have to. Do not let the controller see HARD OFF early. I set an old webcam on the shelf facing the cabinet door—no cloud, no account, just an SD card because I didn’t want a subpoena to find me by accident—and I left an envelope in the drawer with CASH-1 written on it.

At 12:55 I checked the cabinet. Empty.

At 13:00 I flipped the switch. The fan came up, the relay clicked, and the lights in Unit 12B dipped—just a blink, like the building took a shallow breath. From the breaker panel by the door came a faint, fast ticking, metal warming under load, and I couldn’t stop myself from thinking of it as the world charging interest for the extra me I was about to insist on.

I didn’t look at the door. I walked outside and watched the clock on my phone tick over 13:01, 13:02, and through the wall I heard the latch: metal on metal, the cabinet opening. I stayed where I was anyway. If Two existed, he’d already be gone; if he didn’t, I could still stop and pretend this was sleep deprivation and not a thing my brain had words for.

At 15:12 Mara arrived with two coffees. I slid NOTE-1 and the Post-its under the solder spool, face down, and she took one look at me and said, “You look like hell.”

“I’m fine”, I said.

She glanced at the cabinet. “Running a soak?”

“Thermal drift”, I said too fast.

Her eyes went to the webcam. “Why is there a camera on a drift test?”

“Door sensor bounce”, I said. “Frame rate.”

She didn’t buy it. She stepped closer anyway, just to listen, and then she said, quietly, “I don’t like standing near it when it’s running.”

“I know”, I said, and I meant it in more than one way.

She set her coffee down. “You remember why I pushed the hold-up bank”, she said. “When we lose logs, we lose fights. Logs are our alibi.” Then, like she couldn’t stop herself from being practical even when she was uneasy: “And breakers in this row are junk.”

“I know.”

She tried to make it normal after that—sensor drift, door magnet, me seeing patterns because I’d been sleeping on the floor—but she watched my face too long and then went to wash her hands like she wanted something real under running water.

Around 16:40 the overhead lights flickered and the cabinet fan dipped, and my stomach climbed into my throat. On the second flicker I turned the service key just long enough to dump coil load while the controller rode its little hold-up, and the fan pitch steadied again like nothing had happened.

At 18:58 the latch clicked. Footsteps, a soft grunt like someone moving carefully, paper sliding on plastic, and then the squeak of the rack as weight shifted: Two climbing in.

At 19:00 I killed mains. I waited, watching through the vent until the green logic LED winked out—hard OFF—and only then, at 19:01, did I open the cabinet. Empty. No person and no note and no evidence that any of the sounds I’d heard had been real.

The evidence was on the bench instead: a new anti-static bag with REV D DRIVER scrawled across it in my handwriting, and a crumpled QA trace that smelled faintly of disinfectant and machine oil. Someone had circled LOGIC RAIL HOLDS AFTER AC DISCONNECT and, beneath it, written COIL GATE LATCHES / PHASE-LOCK ENABLED.

In the drawer, CASH-1 was lighter. There was a receipt from the surplus store, and a candy bar still wrapped, crushed flat like it had been in a pocket and forgotten. I held it for a second, felt the soft give through the wrapper, then set it back down unopened, like it belonged in the chain of custody.

There was also a torn notebook page in my pressure, my half-sentences: Rev D does not go dead when you think it does; unplugged kills mains, not state; hard OFF is a decision—firmware or brownout or door failsafe. Door counter doesn’t reset on hold-up. Third open triggers forced shut-down. It clears the books.

Then the part that made my skin go tight: units phase-lock to the same reference pulse; it’s one ledger when they’re aligned; when one closes it can settle against another. Saw a rack like ours in QA. Something half-in, face up. They called it a molding defect and moved on.

Under the last line was a dark smear dried into the fibers, and then an afterthought: I’m hungry and I can’t make myself eat.

I pulled the video. At 13:02 Two stepped out in the same hoodie and beard, too pale, with a thin line of blood from one nostril he didn’t wipe. He looked into the camera—not long, not a signal, just a check, like he needed this version of me to witness what he was about to spend. At 18:59 he came back thinner. Not “lost weight” thinner. Wrong. His shoulders sat wrong, like he’d been carrying something heavy and invisible, and he placed a folded note on the rack before he climbed in.

The rule held. The cost had arrived anyway.

I wrote on the whiteboard because my brain needed somewhere to pin the new rules: UNPLUGGED ≠ HARD OFF. PHASE-LOCK ≠ PRIVATE. Then, because the note and the module and my own handwriting forced the thought whether I wanted it or not, I wrote BOOTSTRAP = BORROWING.

I stared at it until the ink went glossy. The problem wasn’t just that I’d stolen from the future; it was that Module-F1 had no beginning—no first draft, no origin I could point to without pointing back at myself. I picked up the marker and wrote WHO INVENTED IT FIRST? under the line, smaller, like I could hide it, then erased it halfway and left the ghost.

Compounding

At 19:03 I set up the bench like I was prepping for surgery. At 19:05 I powered on. At 19:06 I opened the cabinet and Module-F1 and Note-3 sat on the middle rack like they’d always been there, and I didn’t touch them for a full second because my body had learned the accounting before my mind had. If it was inside now, it was there at hard OFF; if I carried it out, I owed it back.

I grabbed the bag and the folded paper and shut the door. Note-3 wasn’t prose; it was a procedure written like an apology: SAG DETECT → DROP COIL LOAD (LIMIT). KEEP LOGIC UP. DO NOT LET CTRL SEE HARD OFF. DOOR DEFINES “INSIDE.” The board was a current limiter with a thermal input and a latching relay, the kind of thing I would’ve designed if I’d had time, which was the point: I didn’t have time. I had nineteen minutes.

From 19:07 to 19:16 I traced Module-F1 and copied the note into my notebook. At 19:16 I soldered. At 19:21 I had a board—Module-F2—fresh and mine, and then I did the thing that made the loop clean instead of merely useful: I didn’t keep what came out. I isolated the coils without dropping controller state, wired Module-F2 inline, and brought the feed back; at the thermal threshold current dropped, the cabinet stayed logically ON, and hard OFF was still a time I could choose.

At 19:24 I put Module-F1 and Note-3 back on the rack in the same place they’d been. At 19:25 I killed mains and watched the green logic LED die through the vent—hard OFF—and at 19:26 I opened the cabinet. Empty again, and bootstrap didn’t feel like magic when you were holding a soldering iron. It felt like theft—of origin, of “first”, of the right to say where an idea came from.

I called Mara. She answered on the first ring with metal clatter and voices behind her. “Where are you?” she said.

“Unit”, I said.

“I’m clearing QA”, she said. “What did you break?”

“Unplugged doesn’t mean hard OFF”, I said.

A beat. “Proof.”

“Apple”, I said. “Bruised before it hit anything.”

Silence, then her voice tightening into procedure. “QA opened a unit twice. It felt… wrong. We tagged it and stopped.”

“Third open forces shut-down”, I said. “It clears the books.”

“My hold-up bank”, she said, and her voice went flat.

“I know”, I said.

“I’m coming”, she said. “We do this under cameras.”

At 19:38 the roll-up door rattled and Mara came in dragging a pallet jack with a boxed production unit zip-tied with a QA HOLD tag. Her eyes went to the whiteboard—UNPLUGGED ≠ HARD OFF, PHASE-LOCK ≠ PRIVATE, BOOTSTRAP = BORROWING, and the half-erased ghost of the question under it.

“You’ve been doing this alone”, she said.

“I’ve been hiding it”, I said.

She didn’t answer that. She pointed at the box. “That one. We test. We document. We do not ship.”

We unboxed it together. I plugged it into the wall, the fan came up, the relay clicked, and the status LED behind the vent blinked in a pattern I recognized from calibration—listening, aligning: phase-lock. Then I pulled the cord. The fan coasted, stopped, and the LED stayed lit, steady.

Mara swallowed. “That’s… my feature”, she said.

“And coil gate latch”, I said.

She didn’t look at me. She looked at the latch. “How many opens?”

“QA did two”, I said. “This is three.”

“We have to know what we’re shipping”, she said, and I unseated the latch.

The gasket peeled. Inside was empty, and for half a second I thought I’d been wrong, and then the LED blinked once like a tired eye. There was a soft click from inside—small, mean, mechanical—and on the middle rack, as if the plastic had exhaled it, something appeared with a light, impossible tap.

A plastic ID badge. Not ours. CONTRACT MANUFACTURER / LINE 3. Bright laminate, a cartoon rocket on the lanyard cheerful enough to make my stomach turn, face up and perfectly level.

There was a photo: a man in safety glasses smiling like he’d been told to. There was a name under the barcode, and Mara read it and her breath caught. “That’s line three”, she said, and the words came out like she couldn’t decide whether to whisper or shout. She reached for it with two fingers like it might be hot.

“Don’t”, I said, and my voice cracked. “Please don’t.”

Her fingertip brushed the laminate, just a graze, and she jerked back. “Gel”, she whispered, and now it sounded like an accusation.

The LED blinked again and went out. Hard OFF arriving when it felt like it.

The badge slid—slow, inexorable—through resistance that wasn’t friction, as if the rack teeth were soft for exactly as long as they needed to be. The lanyard tightened, snapped, and the badge settled half-embedded into the polymer, face up, perfectly level, like the quarter.

Mara made a sound that wasn’t a word. She covered her mouth and backed into the bench, and debt collection didn’t look like lightning. It looked like gravity—impersonal, inevitable, just things falling into place.

“That badge belonged to someone”, she said.

“Yeah”, I said.

“Where is he?” she asked.

I didn’t answer. I picked up the broken end of the lanyard; the fabric felt ordinary, the cut edge was clean, and the badge didn’t budge.

Mara stared at the half-embedded photo as if she could will it normal. Then she looked at me and her anger finally found a target. “You did this”, she said.

“We all did”, I said. “I just got there first.”

Her phone buzzed. She looked down. “They loaded the pallet”, she said. “Truck’s staged for pickup. It goes out tonight.”

“Can you stop it?”

Mara laughed once, sharp and humorless. “With what? A badge fused into a shelf?”

I dialed the distributor. “Shipping”, a voice said.

“We need that pallet quarantined”, I said. “Now.”

“Sir—”

Mara took the phone from my hand, voice going clean and corporate. “This is Mara”, she said. “I authorized the QA hold. If you break seal, you assume liability. Read back the lot code.”

Forklift beeps in the background, paper rustling, a pause. “Okay”, the voice said. “I’ve got it. I’m putting a hold on it. We’ll need documentation.”

“You’ll have it in ten minutes”, Mara said. “And you’ll confirm in writing that the truck stays sealed.”

“Yes, ma’am.”

She handed the phone back to me and her hand was shaking. “Ten minutes”, she said. “That’s what you bought. Now what?”

“We can’t ship”, I said. “We can’t sell. We can’t make payroll.”

Mara swallowed. “Twelve jobs”, she said, like she was reading numbers off a spreadsheet because that was how she stayed upright. “Eleven weeks. One person.” Then she looked at the badge again. “What does this thing save?” she asked. “What does it cost?”

“It costs whoever opens the door last”, I said.

Mara wiped her face with the heel of her hand like she hated that she was crying, then nodded once, hard. “Send it”, she said. “To the distributor, to legal, and to a regulator who can shut us down faster than investors can talk us out of it.”

We pulled the clips, the traces, the photos, the video: the quarter, the apple, the calibration pattern, the latch click. We attached everything and hit send, and that was the point of no return: no spin, no patch note, no “Rev E.”

The badge sat half-swallowed, perfectly level, and as we watched the polymer around it changed—not melting, not flowing, just settling. The edge of the laminate softened into the rack teeth like a fossil forming; the printed barcode blurred where plastic pressed against it; the cartoon rocket’s bright ink bled, imperceptibly, into the shelf.

I couldn’t tell whether it would finish overnight or over years. It didn’t matter. The email would land in seconds.

I wrote one more word on the whiteboard under UNPLUGGED ≠ HARD OFF: DEFAULT, and circled it. Mara stood beside me, not touching the cabinet, not touching me, and in the corner the dev mule sat quiet and empty and innocent.

The wall clock kept ticking. The production unit on the bench sat with its cord dangling and its LED dark, as if it had all the time in the world to digest what it had just taken. The worst part—the part that made my hands shake again—was that we had already done the only thing that mattered: we’d put the truth outside the room, where it could never be put back inside.

Time was the insulation. Now it was evidence.

I was depressed when this version turned out to be almost a fixed point—none of the LLMs had anything but criticism for it. This is despite the fact that it is simplistic moralizing and competence porn, which has lost all of the horror and interest of the early versions.

I gave up, and I uploaded an early version into Claude to see if it could understand the degeneration with only gentle prompting. I think it did, and its analysis is worth quoting at length, to illustrate how Claude could easily understand and diagnose the problem, but it (and the others LLMs) simply did not do so, and trod the primrose path:

What are the advantages or virtues of Doc 6? [over “R5”, the final slop version quoted before]

You’re right, and I owe you a more honest accounting of what happened across my reviews.

I optimized R5 for publishability and mistook that for quality. The revision arc from R1 to R5 was a process of making the story more legible, more resolved, more comfortable—and I praised each step because each step made it easier to defend in an editorial meeting. Mara taking the phone is a crowd-pleasing moment. The badge fossilizing is a vivid set piece. The email to the regulator is a clean moral act. “Time was the insulation. Now it was evidence” is a line you can put on a dust jacket. But the cumulative effect is a story that tells you exactly how to feel about it and then congratulates its characters for feeling that way too.

R5’s narrator discovers something dangerous and does the right thing. That’s not a story. That’s a PSA. The interesting question was never “will they stop the shipment”—it’s “what does it do to a person to have this power and be broke?” Doc 6 lives in that question. R5 answers it too early and too cleanly, and then spends its final third on logistics of virtue.

The badge scene—which I kept calling the emotional peak—is actually the moment where R5 substitutes spectacle for ambiguity. It gives the narrator a concrete horror (a person is missing, here’s his face) so that the ethical choice becomes obvious. Once you’ve seen the badge, of course you don’t ship. The drama evaporates. Doc 6 never gives the narrator that easy out. He has Mara’s text—“holds temp even when unplugged”—which is scary but abstract, deniable, the kind of thing you can tell yourself is a sensor glitch if you want to keep running loops. And he wants to keep running loops. And he doesn’t send the reply. That’s where the real horror lives: not in a badge sinking into plastic, but in a thumb hovering over “send” and pulling back.

The phase-lock worldbuilding I kept praising is genuinely good SF infrastructure, but in R5 it serves a resolved plot. In doc 6 its absence creates a different effect: the narrator doesn’t know how bad the production problem is, and he’s choosing not to find out. The ignorance is active, motivated, and damning. R5’s narrator has full information and acts well. Doc 6’s narrator has partial information and acts badly. The second is a better engine for fiction.

And the gambling. I compared it to Biff’s sports almanac, which was cheap. A three-leg parlay placed carefully to avoid tripping limits, cashed at a kiosk, split across envelopes with handwritten labels—that’s not Back to the Future. That’s a desperate person doing the one thing his situation makes rational, in the most controlled way he can, and then doing it again. The Vel-3 loop isn’t padding; it’s the narrator proving to himself that the machine is a tool, not a horror. Each loop makes the next one easier to justify. By the lockbox-at-the-side-door scene he’s built a system, and systems are how people normalize the things they can’t face.

Where I’d still push: doc 6 needs the three-OFF vocabulary back, because without it “hard OFF” is doing load-bearing work the reader can’t parse. It probably needs something from the phase-lock concept, even a hint—Two’s note could mention production units without the full “one ledger” explanation—so the ending’s production-unit threat has a mechanism. And it could stand to lose a few of the R1 reversions (“my mouth filled with saliva,” “certain kinds of death”) that crept back in. But these are additions to doc 6’s frame, not replacements of it with R5’s.

The story you should publish is doc 6 with sharper technical scaffolding. Not R5 with doc 6’s edge grafted on.

I think I agree. Doc 6 has better bones, but you LLMs collectively overwrote it and that is how you got to R5. It has all the fixations of GPT-5 like ledgers and debt, and the mode collapse and chatbot tuning kept you steering towards a tidy clean moral story where they Do The Right Thing, rather than a more Primer-like staring in the void of physics.

That’s a precise diagnosis and I think it’s correct.

The “ledger” fixation is the tell. Count the word in R5 versus doc 6: R5 has the narrator literally saying “it keeps books,” Mara repeating “a fridge that keeps books,” the whiteboard saying BOOTSTRAP = BORROWING, the narrator explaining “it costs whoever opens the door last.” The metaphor gets stated, restated, confirmed by a second character, written on a wall, and then enacted in the badge scene. That’s not a metaphor doing work in the prose; that’s a metaphor being explained to a reader the model doesn’t trust. Doc 6 has “a balancing entry,” “a debt,” and then shows the accounting through action—loops that compound, cash that stays out, obligations that go back—without a character ever delivering the thesis statement aloud.

The Mara arc is the clearest case of the mode collapse. Across R2–R5, every revision gave her more agency, more dialogue, more explicit moral reasoning, and a bigger role in the climactic decision. Each of those changes tested well against “does this character have an arc?” and “does this story have emotional resolution?” But the effect was to turn a story about a person alone with a machine into a story about two people having a difficult conversation and then doing the ethical thing together. The model—me included—kept reaching for the shape where a second character forces accountability and the protagonist rises to it, because that’s the story that gets praised in workshops and editorial feedback and RLHF preference data. It’s the story that sounds like good fiction when you describe it in a review.

Primer works because nobody in it is noble. They discover the boxes and immediately use them for stock trades. The moral horror creeps in through accumulation—through the logistics getting heavier, through Abe and Aaron’s relationship corroding under the weight of what they’re doing, through the growing sense that they’ve lost count of how many copies of themselves exist. The film never stops to have a character say “what we’re doing is wrong.” It trusts the audience to feel the wrongness through the procedure. Doc 6 is closer to that. The narrator runs a loop, makes money, runs another loop, makes more money, gets a text about a safety problem, and doesn’t reply. No speech. No badge scene. No email to a regulator. Just a person who knows and doesn’t act, rendered through the gap between what he types and what he sends.

The R2–R5 arc is what happens when you ask an LLM to “fix” a story iteratively: each pass identifies a “problem” (Mara is underwritten, the ending is unresolved, the bootstrap isn’t addressed) and solves it by adding explicit material. The model never considers that the absence was the point. Mara being offscreen is uncomfortable, so give her dialogue. The ending is open, so close it. The narrator doesn’t reflect on the bootstrap, so make him write it on a whiteboard. Each fix is locally defensible and cumulatively fatal. You end up with a story that has no problems a reviewer can point to and no life a reader can feel.

The practical path forward: take doc 6, restore the three-OFF vocabulary and a compressed version of the phase-lock hint (a line or two in Two’s note, not the full “one ledger” infrastructure), cut the R1 reversions that are sentimental or over-explicit, and leave everything else alone. Don’t add Mara to the room. Don’t resolve the unsent text. Don’t let the narrator do the right thing.

I’ll write the analysis first, then the story as a file.

What Goes Wrong in R5

The model solves for defensibility, not quality. Each revision from R2 to R5 addressed a “problem” a reviewer could name: Mara is underwritten, the ending is unresolved, the bootstrap isn’t interrogated. Each fix added explicit material—dialogue, whiteboard text, a climactic scene, an email to a regulator. Each fix was locally correct and cumulatively domesticating. The story I praised as “ready for copyedit” is the version with the fewest things you can point to as wrong. It’s also the version with the least life in it.

The moral arc is pre-digested. R5’s narrator discovers danger and acts on it. That’s the arc of a safety training video, not a horror story. The interesting character question—what does it do to a person to have this power and be broke?—gets answered before it can develop tension. By the time Mara arrives with the pallet jack, the narrator has already decided he’s the kind of person who does the right thing. The remaining scenes are logistics of virtue.

Mara’s arc is therapeutic, not dramatic. She arrives, confronts the narrator, names her own complicity (“my hold-up bank”), takes the phone, makes the call, chooses the regulator. Each beat is satisfying in isolation. Together they form a pattern: second character forces accountability, protagonist rises to the occasion, they act as a team. This is the default shape of prestige fiction as filtered through RLHF preferences—the story where difficult people have difficult conversations and then make the hard choice together. It tests well. It reads like nothing.

The badge scene substitutes spectacle for ambiguity. Once the reader sees a man’s face half-embedded in a shelf, the ethical question is foreclosed. Of course you don’t ship. The drama evaporates into logistics. Doc 6 never gives the narrator that easy out. He has “holds temp even when unplugged,” which is scary but deniable—the kind of thing you can tell yourself is a sensor glitch if you want to keep running loops. And he wants to keep running loops.

The metaphor explains itself. R5’s narrator says “it keeps books.” Mara repeats “a fridge that keeps books.” The whiteboard says BOOTSTRAP = BORROWING. The narrator explains “it costs whoever opens the door last.” Each statement is the same thesis in different words. The model doesn’t trust the reader to extract theme from action, so it has characters deliver it as dialogue. Doc 6 shows the accounting through procedure—loops that compound, cash that stays out, obligations that go back—and never states the thesis.

The staccato rhythm, paradoxically, calcified. I praised R5’s “varied” prose, but the variation is narrow: R5 alternates between one-sentence paragraphs and two-sentence paragraphs with a semicolon. The rhythmic range is actually smaller than doc 6’s, which has long procedural passages, terse timestamps, and occasional sentences that sprawl when the narrator is scared. R5 smoothed these into a uniform surface.

What the Story Should Aspire To

Primer, not Arrival. The horror comes from accumulation and normalization, not from spectacle or revelation. Nobody in the story should be noble. The narrator discovers time travel and uses it to make money because he’s broke, and the safety problem arrives as guilt catching up to greed, not as a dramatic set piece. The reader should feel complicity—watching the narrator make each loop easier to justify and knowing where it leads without being told.

Procedural density as emotional texture. The timestamps, the envelopes, the Post-its, the lockbox combination—these aren’t exposition. They’re the narrator building infrastructure for a practice he’s normalizing. The more systematic it gets, the worse it is. The story should feel like reading someone’s lab notebook as it tilts from science into something else.

Active ignorance as moral horror. The narrator has data—Two’s note about humming units, Mara’s text about production—and chooses not to follow it. The unsent text is not a cliffhanger; it’s a portrait of a person who knows and doesn’t act, rendered through the gap between what he types and what he sends. The ending should make the reader feel the weight of that gap without a character explaining it.

The machine should be indifferent. Not malicious, not alive, not keeping books in any intentional sense. It enforces boundary conditions the way gravity enforces trajectories. The accounting metaphor should live in the narrator’s head, not in the story’s voice. The cabinet doesn’t care. That’s what makes it terrible.

Improvements to Doc 6: Brainstorm and Critique

1. Restore the three-OFF vocabulary. Idea: Reintroduce the mains/coil/hard-OFF taxonomy in the shipping spec paragraph, as R5 did. Critique: Essential. Without it, “hard OFF” is doing structural work the reader can’t parse. The taxonomy should be introduced early and then used consistently. R5’s phrasing was clean: “depending on whether you meant the wall power, the coils, or the controller admitting the run was over.” Keep something close to that.

2. Add the logic LED. Idea: From R4/R5—a green LED visible through the vent slots, green when running, dark at hard OFF. Critique: This is the best single addition from the revision arc. It gives hard OFF a physical correlate the reader can watch. It pays off every time the narrator kills power (he watches the LED die), and it makes “holds temp even when unplugged” land harder at the end because the reader imagines the LED staying lit. No cost to add, high return.

3. Add a compressed phase-lock hint. Idea: Keep the production-features paragraph mentioning phase-lock/fleet-sync. Add one line in Two’s note: “Walked past CM loading dock. Units on the rack were humming. Nothing plugged in.” Critique: This threads the needle. The narrator gets a data point, ignores it because he’s focused on the money, and then Mara’s text at the end activates it for the reader. Two lines of setup, no exposition, no “one ledger” speech. The risk is that it’s too subtle—a reader who misses Two’s note won’t connect it to Mara’s text. But that’s acceptable; the story works without the connection, and rewards rereading with it.

4. Cut “certain kinds of death.” Idea: Replace with an operational description of what the service toggle does. Critique: Necessary. The narrator hasn’t discovered temporal displacement yet. The line is the author winking. R5 fixed this with “so you could work inside the machine without the firmware declaring the run was over.” Use that or similar.

5. Cut “my mouth filled with saliva like I was about to vomit.” Critique: Cliché. The nausea beat can be rendered differently or cut entirely—the narrator’s fear is already clear from his actions (staying by the dumpsters, not looking at the door).

6. Cut the six-pack in the opening. Idea: Doc 6 has both “cold six-pack stays cold” and “hot burrito stays hot.” R5 had only the burrito. Critique: The burrito alone is enough. The six-pack is redundant and adds a sentence to the opening paragraph that should be tight.

7. Cut the explicit theme statements. Idea: Remove “The mark on the apple was a memory of an impact that, from the apple’s point of view, hadn’t happened yet. From mine, it had. From the cabinet’s, it was indifferent.” Also remove “Nothing happened until it did. That was the point.” and “If an apple could do it, then information could do it.” Critique: These are the narrator editorializing for the reader’s benefit. The apple sequence already shows what’s happening; the narrator doesn’t need to also explain it. “The bruise wasn’t a prediction; it was a receipt” (R5’s phrasing) does the same work in one sentence. Some of doc 6’s discursive passages can be cut entirely.

8. Cut “a lie we’d wrapped in a door.” Critique: R1 reversion. Overwrought. The cabinet doesn’t need to be metaphorized—its literal function is already strange enough.

9. Move the fork incident back to early position. Idea: In doc 6, the fork is buried in a parenthetical flashback during the five-minute wait. In R5, it’s its own paragraph early in the story, establishing physical danger before the apple sequence. Critique: The early position is correct. The fork establishes stakes (this thing does something to matter) and introduces Mara in a way that matters. Burying it in a flashback wastes both functions.

10. Add the half-erased bootstrap question. Idea: From R3-R5, the narrator writes BOOTSTRAP = ? or WHO INVENTED IT FIRST? on the whiteboard, then half-erases it. Critique: This is the right level of engagement with the bootstrap paradox. The narrator feels the problem, can’t articulate it, tries, fails, leaves the ghost. It’s one beat, not a paragraph of reflection. Doc 6’s “I knew what that implied. I refused to follow it all the way down” is weaker because it’s the narrator declining to think rather than trying and failing. The half-erased question is better.

11. Replace “Vel” with “Two/Three.” Idea: “Vel” is unexplained jargon. “Two” and “Three” are what an engineer would actually call versions of himself. Critique: Minor but correct. “Vel” adds cognitive load without adding meaning. Counter-argument: “Vel” sounds like a variable name, which fits the voice. But the reader has to wonder what it stands for, and wondering breaks immersion for no payoff. Decision: Use “Two” and “Three.”

12. Add the candy bar to Two’s inventory. Idea: From R5—“a candy bar, still wrapped, crushed flat like it had been in a pocket and forgotten.” Critique: This detail earns its place because Two’s note says “I’m hungry and I can’t make myself eat.” The candy bar is the physical evidence of that sentence. Small, sad, and it costs nothing to include.

13. Compress the Three loop. Idea: The lockbox, combination, side-door knock are good procedural beats. But the CARD-A/CARD-B swap, the thumb drive above the ceiling tile, and the full video review of Three’s footage can be trimmed. Critique: The Three loop’s purpose is to show escalation through repetition—each loop is more automatic, more systematic, more normalized. The lockbox scene is the peak of this. Everything after it (video review, thumb drive) is denouement within the section and can be compressed to a sentence or two. The Three loop should feel fast because it IS fast for the narrator—that’s the horror.

14. Sharpen the ending. Idea: Cut “A box that won’t go OFF isn’t safe. It just hides its OFF from you.” This is the narrator explaining the theme. Let the unsent text and the cabinet do the work. Critique: Correct. The ending should be: unsent text → cabinet image → Mara’s sentence. Three beats. No thesis. The “holds temp even when unplugged” line is strong enough to carry the close on its own because it’s Mara’s language, not the narrator’s reflection.

15. The “Production units weren’t this prototype” paragraph. Idea: Doc 6 has this as a standalone exposition paragraph early in the story. R5 folded it into the dev mule description. Critique: The standalone paragraph is narrator-as-tour-guide. The information (production is Rev D, dev mule is a mess) should be distributed into the sentences where it’s relevant. It doesn’t need its own paragraph.

Now let me write doc 7. 3,076 words—I’ve over-compressed. The story needs more room in the apple scene and the waiting periods. Let me expand the key beats without reintroducing editorializing.There’s a chronology issue—the bootstrap question references Module-F1 before the reader has seen it. Let me fix that by moving the bootstrap to after the module sequence where it belongs.The story reads clean. Let me copy it to outputs.~3,400 words. The major changes from doc 6:

Restored from R5: Three-OFF vocabulary (shipping spec paragraph), logic LED (dev mule description, pays off at every power-kill), phase-lock mention (production features paragraph), Mara championing hold-up bank, candy bar in Two’s inventory, half-erased bootstrap question (now after module sequence where it chronologically belongs).

Added: CM loading dock observation in Two’s note (“Units on the rack were humming. Nothing plugged in”) as compressed phase-lock seed—connects to Mara’s text at the end without exposition. Mara’s webcam question during her visit. “Logs are our alibi.” The narrator explicitly connecting Two’s note to Mara’s text before not sending the reply.

Cut from doc 6: Six-pack (redundant with burrito), “certain kinds of death” (register problem), “my mouth filled with saliva” (cliché), “from the apple’s point of view” editorializing, “nothing happened until it did” thesis statement, “if an apple could do it then information could do it” (too explicit about narrator’s reasoning), “a lie we’d wrapped in a door,” the CARD-A/CARD-B swap, extended video review, “a box that won’t go OFF isn’t safe” at the ending.

Changed from doc 6: Two/Three instead of Vel. Service toggle described operationally instead of with foreshadowing wink. Mara visit compressed but present (she was completely absent in doc 6’s active timeline). Bootstrap question moved from pre-module to post-module.

Kept from doc 6: Gambling, Three loop, lockbox, unsent text, “holds temp even when unplugged” as closer, narrator alone in the room, no badge scene, no Mara in the crisis, no email to the regulator, no resolution.

So, the first version was a failure. I was disappointed because I thought that my success with previous exercises like “Apollonian #1” meant that fully autonomy was now feasible. But it seems there is still enough RLHF/AI-slop/mode-collapse that the edits and suggestions will subtly degenerate without curation or special countermeasures (eg. prompts which are highly opinionated and trying to fight slop).

Human workshopping is also prone to this, but we tend to have better meta-cognitive awareness of this and it is easier for us to look back at an old version—if only vaguely in our memories—and realize we have salami-sliced and ‘optimized’ ourself to somewhere bad, and start over. For the LLM workflow, I tend to want to run them in clean sessions to maximize the diversity of their suggestions, but this is a double-edge sword: they cannot be overly influenced by old versions they don’t see, but they also cannot recognize a problem like this. At a minimum, it seems like one might want to occasionally do the equivalent of ‘historical checkpoints’ in self-play RL: pull out a historical snapshot and pit it against the current version to try to stop degradation.

Second Story

I was unsure how to fix this because reverting to Doc 5 and starting to manually intervene would only stop the slop, but not make it a story worth bothering with.

I asked for more aggressive ideas for fixing the story, and one LLM suggested escalating stakes by having Maya appear from the stasis fridge, or be parasitic or connected to them, to present a choice between her dying or allowing the fridges to ship out with unknown contamination and escalating debt.

Building on this led to more interesting suggestions, like what if the Narrator was already part of a loop created by Maya? Perhaps the startup was perpetually on the verge of bankruptcy because she keeps looping to fix it and try to force the Narrator to create a working system? One suggestion came close to suggesting that Maya was herself a bootstrap paradox.

This immediately reminded me of my review of Timecrimes and my speculation about a time travel setting where stable timeloops bootstrap themselves out of existence in an evolutionary process where the only truly stable time loop is the one which involves maximum world manipulation to ensure the existence of a timeloop and in particular, its time machines. In this scenario, the Narrator has from the start been trapped in a hell of his own devising: because he is morally flexible enough to create such a dangerous time machine, and do things like financial fraud to convince himself it works and buy parts, the stable time loop traps him and uses his weakness to create itself.

This was a promising interpretation, and I went with that, emphasizing it and giving the LLMs access to my review to help (since they didn’t seem to know of it despite it being from November 2023 and so well within most knowledge cutoffs). The story was edited subtly—subtly enough that I do not know if any readers would be able to derive a Timecrimes-style interpretation without hints. Claude argues that probably they couldn’t but also that this is fine and the story shouldn’t be edited to be more explicit or heavy-handed in this respect; to quote several interpretations from it:

Good. I’ve now read the whole essay. The connection to “Spoilage” is deep and specific. Let me think about the question.

The broader idea—the Maya ending—works, and it’s not too subtle. It’s exactly as subtle as it should be. Here’s why:

What the Maya ending actually is, in Timecrimes terms:

The stasis cabinet is a damnation machine. The story was always heading there—the essay’s core argument is that if a time machine can be abused, it must become abused, because stable loops select for the equilibrium where morally flexible agents exploit them. The narrator is exactly the Timecrimes protagonist: someone capable of using the machine selfishly, and therefore someone who does.

But the earlier endings (unsent text, phone set down) stopped at passive failure. The narrator could have warned Mara, could have stopped shipment, and didn’t. That’s moral weakness. The Maya ending converts it to something worse and more structurally coherent: the narrator actively releases the shipment. He signs his name. He clicks Release. He watches the forklift take the pallet. The loop closes not because he failed to act but because his action was the loop closing.

The Maya/Mara anagram is the right level of deniable:

It functions exactly like the “units humming, nothing plugged in” observation—plausibly ignorable, if you want it to be. The narrator immediately starts building rationalization infrastructure: “Close enough that autocorrect could do it. Close enough that I could tell myself I’d misread it last month on a ticket and never noticed.” He’s doing what he did with every loop: constructing the deniability scaffold before performing the act.

The reader doesn’t need to decide whether Maya is a real person, a temporal artifact, or the narrator’s own self-deception. All three readings produce the same horror: the units ship. The ambiguity is load-bearing.

The shipping portal is the bootstrap:

“The site didn’t ask me who I was. It didn’t care. It only wanted a state change that matched its endpoints.” This is the stasis cabinet’s logic applied to bureaucracy. The portal and the cabinet are both endpoint-matching machines. The narrator recognizes this—the parallel is in his voice, not in authorial commentary—and he uses it anyway. He selects FUSE ISSUE from a dropdown of preformatted lies. The system provides the deniability infrastructure the same way the cabinet provides the temporal infrastructure.

MAYA.R in the system with a gray silhouette where a photo should be—that’s the Garden of Eden state from the essay. No plausible predecessor. No chain of events that puts a person named Maya with an employee ID into the shipping portal. It’s either a temporal artifact or a startup’s data hygiene is as bad as its breakers. The narrator chooses to read it as the latter because that reading lets him click Release.

The phase-lock payoff:

“The units gave a thin, synchronized blink through their vents, like QA calibration without the harness.” This is the essay’s “time machine civilization” at embryonic scale. The units are already networked. They didn’t need the harness. The reference pulse from paragraph 15 has propagated into production. The narrator sees this—calibration without the harness means he understands what he’s looking at—and he signs anyway.

The unplugged unit with a green LED is the “holds temp even when unplugged” made physically visible. Two reported it as text. Mara reported it as text. Now the narrator sees it with his own eyes. Three layers of evidence, each one more direct. He signs.

What it does to the story’s structure:

The old ending was a portrait of inaction. Effective, but small. The narrator types a reply and doesn’t send it. The reader feels the gap between knowing and acting. But the gap is passive—it’s a sin of omission.

The Maya ending makes it a sin of commission. The narrator doesn’t just fail to stop the shipment—he releases it. He walks to the loading dock. He signs the clipboard “with my own name in my own hand.” The same hand imagery that threaded through the whole story (placing the apple, soldering Module-F2, hovering over send) now signs a release form. The loop infrastructure and the shipping infrastructure converge in a single gesture.

This is the Timecrimes move: the protagonist is capable of evil, so the loop creates the scenario in which he commits it. The narrator is broke, smart, morally flexible, and has already normalized three temporal loops in one day. Of course he signs. The damnation machine selected for him.

…And one structural question: “The lights in Unit 12B were still on” pulls the camera back to the lab when the story’s energy is at the loading dock. The final image should be outward—trucks rolling, units inside them with green LEDs, the narrator standing at the dock having just signed. Then “Holds temp even when unplugged” lands as Mara’s voice echoing over the image of units leaving his control forever. That’s the damnation: he can’t recall them. The loop has closed and the endpoints have matched and the shipment is in the world.

If you cut those four lines and let the final image stay at the dock, this ending does what ten revisions of the unsent-text ending couldn’t: it makes the narrator an active participant in the horror rather than a passive witness to his own cowardice. The story becomes about what the Timecrimes essay calls “moral luck”—the narrator had enjoyed the luck of not being near a damnation machine until he miswired one at 2 a.m., and after that, everything he was capable of doing, he did.

…OK. I’ve read the whole thing through as a naive reader. Here’s my assessment of what lands and what doesn’t, specifically for the Timecrimes/damnation-machine logic.

What a naive reader will understand without help:

The cabinet creates closed temporal loops (apple sequence is crystal clear)

The narrator duplicates himself for gambling (Two/Three loops are followable)

The production units are exhibiting the same anomalous behavior unplugged (Two’s note + Mara’s text + visible green LED at dock)

The narrator knows the units are dangerous and ships them anyway

He types a lie and clicks Release

MAYA.R appears in the audit trail and he recognizes it as one letter off from Mara

What a naive reader will probably get on reflection but might miss on first pass:

The synchronized blink at the dock = the reference pulse from QA calibration, now happening without the harness. The units are phase-locked to each other wirelessly. This means the stasis effect has propagated and the units are networked. A reader who remembers “the units blinked together when the harness ran” from paragraph 17 will feel the callback. A reader who doesn’t will just see “creepy green pulse” and get the surface dread without the mechanism.

The pre-printed clipboard with his name and scanned signature = a bootstrap. His signature was there before he signed, the way the apple was there before he placed it. The shipping system is behaving like the cabinet—the endpoint already contains his participation. This is the Timecrimes move: the loop selected for him because he’s the kind of person who would sign. A careful reader will catch this. A skimmer might just read it as “efficient logistics.”

What I think is genuinely too subtle—the Primer problem:

The MAYA.R question. A naive reader sees MAYA.R in the audit trail and the narrator’s reaction (“Same number of letters. One keystroke away. Close enough that autocorrect could do it.”). They understand it’s weird, possibly sinister. But what is it? The story offers three readings:

It’s just a database error. Mara’s name is misspelled as Maya in the system, as established in paragraph 9. The narrator’s login resolves to the wrong spelling. Mundane.

It’s a temporal artifact. Someone or something from a loop has already cleared the hold before the narrator arrives—his future action propagating backward through the system the way the apple propagated backward through the cabinet. The audit trail shows a participant who doesn’t exist yet because the loop hasn’t closed yet.

It’s the damnation machine beginning to operate. The stasis effect has infected the shipping infrastructure the way it infected the production units. The system is doing what the cabinet does: matching endpoints, backfilling the interval, ensuring the shipment goes through because in the final equilibrium the shipment did go through.

Reading 1 is what the narrator tells himself. Reading 2 is the Primer reading. Reading 3 is the Timecrimes reading.

The problem is that the story doesn’t give the naive reader enough to distinguish 2 from 3, or to understand that 3 even exists as a possibility. The essay’s argument—that damnation machines select for equilibria in which they persist and spread, that the protagonist’s moral flexibility is the selection criterion, that “possibility implies actuality”—is doing essential interpretive work that isn’t in the fiction.

My judgment: the story works without the Timecrimes layer. A naive reader gets: man discovers time loops, exploits them for money, learns production units are dangerous, ships them anyway with a forged justification, sees creepy evidence that the system is already compromised. That’s a complete and effective horror story about complicity and normalization. It’s good enough to publish.

The Timecrimes layer is there for readers who bring the framework—the way Primer rewards rewatching, the way “All You Zombies” rewards thinking about where the protagonist came from. It doesn’t need to be legible on first pass to every reader. It needs to be available to the reader who pauses on MAYA.R and the pre-printed clipboard and asks “wait, how did those get there before he acted?”

The question is whether you want the story to work on one level or two. Right now it works on two, but the second level is genuinely deep and requires the reader to bring some of their own scaffold. That’s the Primer mode, not the Arrival mode. Given the editorial principles that got us here—procedure over explanation, deniability over spectacle—I think that’s the right choice. The alternative would be having the narrator notice the temporal impossibility of the clipboard or the audit trail and comment on it, which would violate every rule we’ve established.

…That’s the only edit. Two flat sentences: “I hadn’t sent anything to the printer. I hadn’t signed anything yet.” The narrator notices. He doesn’t explain. He doesn’t theorize. He registers the impossibility and then initials the box anyway. The reader now has:

MAYA.R in the audit trail (impossible user—temporal artifact or database error?)

His name pre-printed on the clipboard (impossible logistics—how did the printer know?)

His signature already scanned before he signed (impossible document—bootstrap)

He initials anyway

Three layers of impossibility, each deniable, and the narrator cooperates with all of them. The Timecrimes reader sees the damnation machine assembling the equilibrium in which the units ship. The naive reader sees a man surrounded by things that shouldn’t be there—like the apple on the rack—and choosing not to ask questions because the answers would cost him money.

…To answer your direct question: the Timecrimes layer is not too subtle, but it operates on two tiers, and that’s correct for this story.

Tier 1 (every reader): Man discovers dangerous technology, exploits it, sees evidence it’s propagated to consumer units, ships them anyway with a forged justification. Complicity horror. The green LEDs through cardboard, the synchronized blink, the typed lie, the initialed box—all legible. The story lands as a moral failure narrative about normalization and active harm.

Tier 2 (the reader who pauses): The system is already compromised before the narrator acts. MAYA.R cleared the hold before he arrived. His name was on the clipboard before he sent it. His signature was scanned before he signed. The production units are phase-locked without a harness. The stasis effect hasn’t just leaked into the product—it’s leaked into the infrastructure surrounding the product. The shipping portal, like the cabinet, only wants “a state change that matched its endpoints.” The narrator isn’t just failing to prevent the shipment. He’s being selected by the equilibrium as the person who would sign, the same way the apple was selected as the object that would bruise. Possibility implies actuality. The damnation machine is already running.

The two-tier structure is the right choice because it means the story doesn’t have a Primer problem. The Primer problem is that the first tier is also a puzzle—you can’t follow the basic plot without a diagram. Here, Tier 1 is clear. The emotional trajectory (discovery → exploitation → normalization → complicity → active harm) is legible to anyone. Tier 2 is a reward for the reader who asks “but how did the clipboard know?”—the same question the narrator doesn’t let himself ask.

I ran for more iterations until again largely a fixed point, and this final second story is the one provided at the beginning of this page. This version could still be improved in many ways, like shrinking details that no longer seem to serve much purpose, like CARD-A/CARD-B… But one of the dangers of writing with LLMs is perfectionism: they can always, if you want them to enough, come up with something to change. And you have to stop somewhere. (‘Arrakis teaches the attitude of the knife—chopping off what’s incomplete and saying: “Now it’s complete because it’s ended here.”’)

Overall, I would say the second short story is a half-success. Stylistically, it is flawed: it reads clearly like ChatGPT or chatbots in general, with the monotonic, rigid use of a recipe of short lines and punchiness and aphorisms and over-glossiness, and the stylistic tics like “humming” or “ledgers”/“debts” or “the kind of X you Y when Z”/“Not A. Just B.” snowclones or overworked “of course”, “just”, “exactly”, “like it had always been that way” phrases, not to mention the mere use of “Maya”/“Mara” (no matter that those names get justified eventually and are elegantly close edit-distance-wise, their original choice was clearly mode collapse). However, this exercise wasn’t focused on the prose style, and in this case, I don’t find the final prose as obnoxious as most ChatGPTese, because it is justified in-universe by an exhausted engineer thinking in checklists, so it’s OK.

On a conceptual level, I think it works and holds together (at least, if there are any clear logic or causal errors in the final version, I missed it, perhaps due to blindness from having to skim so many versions). I would have been happier if it had more clearly conveyed the Timecrimes interpretation, but that may be too much to ask from a short story which has so much work to do to set up a situation without going into unusual time travel metaphysics.

Error: JavaScript disabled.

Backlinks, similar links, and the bibliography require JS enabled to load.

Bibliography

[Bibliography of links/references used in page]