Warranty Void If Regenerated

Folks labeling "AI generated" might be jumping the gun considering OP described his process took him the last couple months and then some for this project.

Call it what you want, but I think this sits better with "AI assisted" and, perhaps, really well supervised full of the human intent behind of it. Then again, labels are strange, we call algorithmic and synthesizer assisted music "electronic" music these days and we still praise musicians who take the time through endless Moog / Ableton fine-tuning sessions to find the perfect loop patterns for their craft.

I could definitely feel the connection between the human author side of this post, thank you for sharing it!

I'm trying to sort out my own emotions on this.

I did not realize this was AI generated while reading it until I came to the comments here... And I feel genuinely had? Like "oh wow, you got me"... I don't like this feeling.

It's certainly the longest thing (I know about) I've taken the time to read that was AI generated. The writing struck me as genuinely good, like something out of The New Yorker. I found the story really enjoyable.

I talked to AI basically all day, yet I am genuinely made uneasy by this.

I really <i>REALLY</i> enjoyed this article and the direction it took me in. I went in with zero preconceptions, just read it straight through, and only after opening the comments did I realize it was largely AI-assisted. Even then, I was very pleasantly surprised. The piece takes you by the hand and leads you through a very deliberate and directed journey. Sure, there are moments where things wobbled a bit like some explanations around specific failures get a little tangled and even contradictory, but none of that registered as “this must be AI.” I’m only noticing those things now, in hindsight, like oh, that’s what that was.

The images hit that sweet spot too. Just enough and few in between to support the plot without getting in the way, just enough to like visually clarify without over-explaining. It all worked together even with minor contradictions around labelling. The inconsistencies wasn't sticky enough to disrupt the plot at all.

Over the MY years I’ve seen an idea play out in movies, books, articles, short stories, that the “humanity only unites when faced with an alien intelligence”. What gets me is how people can enjoy something like this, then immediately recoil once they figure it was actually AI-assisted enough to be largely Ai generated. Does that actually diminish the substance of what they just experienced? I don’t think it does but I'm not gonna argue such a subjective stance.

Someone in the comments suggested tagging AI-assisted work with sth like an “LLM:” prefix, similar to “ShowHN:”. That feels weird to me. LLMs might not be sentient, but they’re clearly capable enough that the output should stand on its own, alongside the intent and effort of whoever’s guiding it. Pre-labeling it just bakes in bias before anyone even engages with the work. It’s not that far off from asking human authors to declare their race or nationality up front. 'cause really if nothing about my direct experience changed, why should my judgment?

In a tech-forward space like HN, I’d expect a stronger bias toward judging things on merit alone. Just read the thing. Let it speak first. I sincerely hope this isn't gonna be an 'LLM vs Humanity' thing 'cause personally, I find the idea of a different kind of intelligence extremely interesting.

I guess I'm an expert on LLM-isms somehow, I thought they were still plentiful. They're plentiful at the start but get significantly worse near the end, so I'm guessing you spent more time polishing up the first 2/3rds or so.

But I was able to get through the text, it's pretty good, you did great work cleaning it up. There's just a bit more to do to my taste.

The story is good.

that's funny, i know where this story is set (i grew up there) - or at least, the place Claude was basing things off of

some inconsistencies that stuck out/i found interesting:

- HWY 29 doesnt run through marshfield, its about 15 miles north.

- not a lot of people grow cabbage in central wisconsin ;)

- no corrugated sheet metal buildings like in the first image around there

- i dont think theres a county road K near Marshfield - not in Marathon county at least

fwiw i think this story is neat, but wrong about farmers and their outlooks - agriculture is probably one of the most data-driven industries out there, there are not many family farmers left (the kinds of farmers depicted in this story), it is largely industrial scale at this point.

All that said, as a fictional experiment its pretty cool!

> The milk pricing tool consumed the feed tool’s output as one of its cost inputs. The format change hadn’t broken the connection — the data still flowed — but it had caused the pricing tool to misparse one field, reading a per-head cost as a per-hundredweight cost, which made the feed expenses look much higher than they were, which made the margin calculations come out lower, which made the recommended prices drop. “You changed your feed tool,” Tom said.

“Yeah, I updated the silage ratios. What does that have to do with milk prices?”

“Everything.”

He showed Ethan the chain: feed tool regenerated → output format shifted → pricing tool misparsed → margins calculated wrong → prices dropped → contracts auto-negotiated at below-market rates. Five links, each one individually innocuous, collectively costing Ethan roughly $14,000.

Ethan looked ill.

--

I've re-read this a few times now, and can't work out how the interpreted price of feed going up and the interpreted margins going down results in a program setting lower prices on the resulting milk? I feel like this must have gotten reversed in the author's mind, since it's not like it's a typo, there are multiple references in the story for this cause and effect. Am I missing something?

[Edited for clarity]

One thing I'll note about this is that the writing reminds me of the much contested "MFA workshop" style that has launched a thousand think pieces.

---

The story was decent! I thought it was insightful and it made me reconsider some aspects of AI use. I am skeptical that an AI could write something on par with the Iliad, or Anna Karenina -- but perhaps I will be disabused of that notion someday. Still, this is a level of quality I am surprised to see to come out of an AI (though, as in your story, the LLM seemed to require its own "choreographer" in the form of your editing and polishing). Very thought provoking.

I will say this is one of the few pieces of prose I've read that was AI generated that didn't immediately jump out as it (a couple of inconsistencies eventually grabbed me enough to come to the comments and see your post details which mention it - I'd clicked through from the HN homepage), so your polishing definitely worked! Quite a neat little story

The LLM-ness isn't a hard problem to fix. Break it into sections, run each through an LLM a few times to catch logic issues, use different AIs to double-check. For the writing style, if the author just read it carefully, they can definitely spot the things Claude keeps repeating, and tell it not to do that.

But honestly, the ideas here are really good. The cascading failure from a weather model update, the spaghetti problem with forty tools nobody designed as a system, the $4 toggle switch being the most important tool --- that's sharper thinking about AI than most serious essays on the topic.

A lot of people who publish regularly can't write to this level of thinking. The prose could be cleaner, sure, but it made me think, which is more than most stories do.

This struck me:

"The tool had changed. The domain had not. People who understood the domain and could also diagnose specification problems were the most valuable people in any industry, and most of them, like Tom, had arrived at the job sideways from something else."

People my age and older arrived in the software business sideways too; in my case from physics and electronics. My background in physics was a great help to me later when programming in the domain of electrical machines because I could speak both languages so to say.

Much grander people than me came into software sideways as I was reminded when reading Bertrand Meyer's in memoriam of Tony Hoare; Tony Hoare's first degree was classics at Oxford.

So perhaps we aren't entering a new phase, merely returning to our roots with new tools.

When I noticed the article header image was generated with AI my interest in reading the article itself dropped to zero.

A fun read!

I'm mildly thrown off by some inconsistencies. Carol says "I’ve been under-watering that spot on purpose for thirty years," and then a paragraph down Tom's thoughts say "Carol didn’t know that she under-watered the clay spot." Carol considers a drip irrigation timer the last acceptable innovation, but then the illustration points to the greenhouse as the last acceptable illustration. Several other things as well, mostly in the illustrations.

Are these real inconsistencies or am I misunderstanding? Was this story AI-assisted (in part or all)? Is this meta-commentary?

This was good, but I think it could have been 10% as long and still conveyed the ultimate metaphor you were going after. The specifics about intricate farming details (which are apparently wrong in multiple places, according to other commenters) are ultimately kind of unnecessary IMO.

Interesting work, nonetheless. I’d check out Kafka’s short stories and aphorisms for more of what I mean. They are very short, yet very metaphorically dense.

I'm very impressed that was written by an LLM.

Does that make the OP an "authoring mechanic"? Or an "AI editor"?

Douglas Adams had it right, the problem is not that the answer was useless, it was that people didn't know what the right question was.

Awesome that LLM generated and still an engaging account. Automated testing (as a software improvement technique) is an AI blind spot. That tweak of spec is the iterative cycle, with no mention of additional automated tests is telling.

Around the part where Margaret explains the problem to Tom , and started to feel annoyed. I could tell it was a LLM trying to fit a sci fi novella style of writing. And it was doing a good job , it was certainly better than 90% of posts ive read in the last 6 months.

Dont know why that makes me annoyed, maybe cause its the depressing seriousness of being a 'prompter' and the americana framing of it.

I do enjoy this sort of speculative fiction that imagines though future consequences of something in its early stages, like AI is right now. There are some interesting ideas in here about where the work will shift.

However, I do wonder if it is a bit too hung up on the current state of the technology, and the current issues we are facing. For example, the idea that the AI coded tools won't be able to handle (or even detect) that upstream data has changed format or methodology. Why wouldn't this be something that AI just learns to deal with? There us nothing inherent in the problem that is impossible for a computer to handle. There is no reason to think AIs can't learn how to code defensively for this sort of thing. Even if it is something that requires active monitoring and remediation, surely even today's AIs could be programmed to monitor for these sorts of changes, and have them modify existing code when to match the change when they occur. In the future, this will likely be even easier.

The same thing is true with the 'orchestration' job. People already have begun to solve this issue, with the idea of a 'supervisor' agent that is designing the overall system, and delegating tasks to the sub-systems. The supervisor agent can create and enforce the contracts between the various sub-systems. There is no reason to think this wont get even better.

We are SO early in this AI journey that I don't think we can yet fully understand what is simply impossible for an AI to ever accomplish and what we just haven't figure out yet.

I very much enjoyed the read

would you be open to share the process?

Nanoclaw is the first hint I've seen of new type of software, user-customizeable code. It's not spec-to-software like in the story, but it is rather interesting. You fork it and then when you add features it self-modifies. I haven't looked deeply, but I'm not sure how you get updates after that, I guess you can probably have it pull and merge itself for a while but if you ever get to where you can't merge anymore, I'm not sure what you do.

As for spec-to-software - I am still pretty unsure about this. Right now of course we are not really that close, it takes too much iteration from a prompt to a usable piece of software, and even then you need to have a good prompt. I'm also not sure about re-generating due to variations on what the result might be. The space of acceptable solutions isn't just one program, it's lots, and if you get a random acceptable solution that might be fine for original generation, but it may be extremely annoying to randomly get a different acceptable solution when regenerating, as you need to re-learn how to use it (thinking about UI specifically here.) Maybe these are the same problem, once you can one-shot the software from a spec maybe you will not have much variation on the solution since you aren't doing a somewhat random walk there iterating on the result.

I also don't know if many users really want to generate their own solutions. That's putting a lot of work on the user to even know what a good idea is. Figuring out what the good ideas are is already a huge part of making software, probably harder than implementing it. Maybe small-(ish) businesses will, like the farmers in the story, but end-users, maybe not, at least not in general.

I do think there is SOMETHING to all this, but it's really hard to predict what it's gonna look like, which is why I appreciate this piece so much.

LLM's also do well with writing parables, so try something like: "write a parable about a software engineer battle against the compiler and discovering that letting go of control and letting the compiler help him build better applications. The style can be where the developer is a toad, but also a monk, and the compiler is a snake.". You can do it with any profession ("doctor vs management", "nurse working overtime") and it can write very insightful parables.

Reading this was a roller coaster for me.

Because of a bad habit reading comments before the link I knew it was AI. I read it regardless, and... I still enjoyed it!

I'm very much not a writer or a critic, so my definition of good writing is likely very low. Yet I can't shake off this weird feeling that I truly enjoyed the writing and felt the emotions, _while_ knowing it's LLM.

I'm guessing that human after touch is what made it pleasant to read. I'd love to see the commit history of the process. Fun times we live in!

> Tom pulled up the tool’s specification on his diagnostic display. This was always the first step: read the spec, not the code. Clearly this writer has never felt the frustration of CC telling them a feature was never a part of the plan, because it overwrote the plan and then compacted.

When I saw this the other day -- and it just went on and on, like a good human author who was going to write this kind of story probably wouldn't -- I looked for a note that it was AI-generated, and I didn't find it.

All I found was a human name given as the author.

We might generously say that the AI was a ghostwriter, or an unattributed collaboration with a ghostwriter, which IIUC is sometimes considered OK within the field of writing. But LLMs carry additional ethical baggage in the minds of writers. I think you won't find a sympathetic ear from professional writers on this.

I understand enthusiasm about tweaking AI, and/or enthusiasm about the commercial potential of that right now. But I'm disappointed to find an AI-generated article pushed on HN under the false pretense of being human-written. Especially an article that requires considerable investment of time even to skim.

I liked it. It has a similar feel to an Andy Weir "The martian" type of novel.

I wonder if this reads like an L. Ron Hubbard work because he was so.fucking.prolific, that his tomes have an outsized representation in the training data.

The whole premise seems offensive. With right-to-repair being on the forefront of many farmers' minds after being stung time and time again by the likes of John Deere, I cannot (or rather, do not want to) imagine a future where an economy is in large part predicated upon tokens one would buy from some giant conglomerate, monopoly or cartel. Never mind right-to-repair, it's pretty clear the direction we're headed (and so many people on this web site especially, seem to be on board with) would strip us of even the right or privilege to own.

What a miserable hellscape we seem so ready to plunge headlong into.

The (very clearly AI-generated) watercolors were an immediate sign to be wary of this. But I read it because I liked the first paragraphs.

The prose is decent, I like the premise, thought provoking idea.

One issue though: I had to use firefox' reader mode, because the contrast between text and background was terrible.

It summarized the nature of humans today nicely. We are ready to pay any amount nice, but when it gets to subscription mode we are not going to pay even 10x less than the one-time.

"This was the mechanic’s paradox: the cheaper you were relative to the cost of failure, the more your clients needed you; and the more they needed you, the more they resisted the implication that they’d need you again."

This is my common issue from building websites for SMEs. It's not until Google updates their algorithm - killing their ranking and their sales leads slow that you hear from them.

There is wisdom in constantly up-selling to your customers (we offer management services, SEO and are cautiously moving in AIO), they may say no, but you have a fall back that you offered things that would have mitigated their current crisis.

Thanks for sharing. This was an amazing read. I’d love to see novels with similar style stories about speculative near future tech and world.

Your polishing work made a difference! The prose is like every other work of science fiction I've read.

It's written like this is a dystopia but billing $180/45 minutes in rural low cost of living area sounds awesome. And the choreographer billing "more than a truck" for three weeks? The dream!

I enjoyed this very much. But I have to wonder, was this written by Claude?

Edit: got it right!

https://news.ycombinator.com/item?id=47419681

There's a bit of a tradition of introducing engineering ideas through stories. I remember a novella which was used to introduce something like MRP II (https://en.wikipedia.org/wiki/Material_requirements_planning) in the 80's. One of the reasons I think it works is that it keeps a focus on the human elements - like why Tom fitted the switch in your story. I remember automating a lab system back in 1985, which would bring in £1000 per day. Two weeks later I found out that the reason it wasn't in use was that the user wanted an amber monitor rather than a green one. I fitted the switch.

I don't know if this is what the future will look like, but this looks realistic. And if my non-existent grandson starts re-coding my business without asking, he's going to spend the next six months using K&R C.

I really enjoyed fantasy part of many small farmers. It felt rustic. However based on my understanding the modern world is moving towards megacorps and economies of scale.

That it was largely/mostly generated by Claude adds a certain poignancy to it.

As an allegory it reminds a lot of one I read as a teen: Joshua by Joseph Girzone. Not a literary masterpiece but a cleaver thought-raising story.

I was going to say the author should try writing fiction because it’s quite engaging, then I realised it’s just AI slop.

It explains why it kind of lost its way towards the end. Another thousand hours of everyone’s time wasted by a slop poster.

A fun read. I was hoping for the title to have some more relevance to the story, like someone who had handcrafted a piece of software and didn’t want others messing with it! Was that ever part of a draft?

This sort of article really needs at least a vague clue as to what it is about.

It's a long article and from skimming I see chat of farming, software, GPS. I can't tell whether this is worth investing time to read if I can't even tell what it may be about

I started reading this and it gave a strong whiff of Richard Stallman’s “the right to read” - once dystopian and now a commonplace.

Then I started scrolling and thought the author was just verbose like RMS.

When it just kept going I was just mad to have fallen into the AI tarpit.

Fun idea. 5x too long. I need to calibrate my ai spidey sense better.

Often suggested by optimistic podcast guests these days: the as-yet-unknown new careers that will replace the familiar old ones and thus give employment in the AI era. I think your story is more a commentary on the current AI goldrush than an insight into future careers.

This is such a good written fiction story. Well done. And the best part: I can see myself as Tom.

So, in the past, your stories were warrant-eed? But no longer?

I can see this future happening!

My favorite part was the illustration from inside the car. The rear-view mirror clearly shows un-mirrored store signs.

Prompts in, garbage out.

I used to live in Marshfield WI. It's kind of jarring to see it mentioned "in the real world", the the extent that HN resembles that.

I don't oppose reading AI generated content in principle, but because it's free to generate, I always am less likely to read super long prose that is AI generated. So the question is whether someone has taken the time to keep it as long as necessary but not longer. Or if there are ways to make it easier for me to commit to the experience, with a sort of TLDR

I stopped to read because I had the feel that the writer has no plan about what he was writing. It's completely bullshit. Software regenerating, changing Requirements in a product thats delivered and comes without source. Completely bullshit. When I now read here that it's AI, I'm happy to see that AI is still not capable of writing senseful texts.

excellent story, it was both interesting and mildly terrifying. to think that one day software could be malleable seems so wrong to me - you would think having deterministic results is important for programming - and yet with "vibe coding" that really seems to be where it's going.

this is such a beautiful essay. thank you op for posting. made my day :)

this was a ridiculously pointless story, I stopped after the second paragraph and came here to ask politely what was the point of it

what was my surprise when I read it was AI-generated