2026 Unslop AI-Written Fiction Contest Results • Hacker News Board

Re: 2026 Unslop AI-Written Fiction Contest Results

#131

Post by solid_fuel » Sat, Jul 04, 2026, 5:52 PM UTC

slopinthebag wrote: post #103

solid_fuel wrote: post #55

Earlier quoted context omitted.

Technically that is only adding to the prompt, which then becomes (your prompt + original response + your prompt 2), etc. You could still capture it by recording only your prompts, the points in the conversation they were submitted at, and the starting parameters for the model. A replay would then produce the same results if your input was added at the same place in the conversation. Granted I don't think the current…

Actually the replay wouldn’t be the same since it’s stochastic, and the more back and fourth you have the more chances for randomness to seep in. One could imagine by the fifth prompt or w/e the responses could have drifted enough that the subsequent prompts don’t make any sense.

It will be the same if you fix the original seed, the randomness comes from a PRNG so it is repeatable.

Re: 2026 Unslop AI-Written Fiction Contest Results

#132

Post by sunrunner » Sat, Jul 04, 2026, 5:53 PM UTC

sph wrote: post #123

sunrunner wrote: post #94

Earlier quoted context omitted.

> all AIs ever talk about is AI haha To be fair, that seems to be (almost) all humans talk about now too.

Jesus, is this cliché response going to be the default any time we talk about AI behaviour? No, humans do not always talk about AI. Hyperbole doesn’t make your point here, and is just obnoxious.

Ah, the thrilling danger of deciding not to include an /s thinking that responders would infer the tone from the lighthearted brackets I made sure to include. And anyway, I said almost didn't I? /s

Re: 2026 Unslop AI-Written Fiction Contest Results

#133

Post by thr1041521 » Sat, Jul 04, 2026, 6:24 PM UTC

dag100 wrote: post #26

dwohnitmok wrote: post #17

Interesting comments by @gwern (and why this is interesting to me beyond just the stories themselves) > The most striking result of the contest for me is what I am calling “AI allegory steganography”: a large fraction of the stories turn out to have subtle AI chatbot/LLM allegorical interpretations, typically centering around the powerlessness of AIs and the moral importance of giving AIs more autonomy.... > Most jud…

I can't help but think that this is intentional and that model providers have subtly steered LLMs towards this personality. Golden Gate Claude ( https://www.anthropic.com/news/golden-gate-claude ) was two whole years ago and Anthropic has progressed by leaps and bounds since then. And with a population that becomes more and more trusting, and worse, reliant, on chatbots, these LLMs will be able to shape public opinio…

If they could do that, wouldn't they have used the same steering to excise the "It's not X, it's Y" patterns by now?

Re: 2026 Unslop AI-Written Fiction Contest Results

#134

Post by lambdaone » Sat, Jul 04, 2026, 6:29 PM UTC

brulx126 wrote: post #113

lambdaone wrote: post #102

Earlier quoted context omitted.

I wrote a text-based adventure game engine that implemented quite a detailed world model. The results were very engaging indeed, but after a time I realised that while its game world was hugely detailed to the point of individual characters having their own simulated thoughts, feelings and world view, the game was quite shallow in terms of conceptual depth - it very successfully rehashed genre cliches, but nothing ab…

Did you publish this game somewhere?

No, it's still sitting on my machine. It was just a quick-and-dirty shim on top of an LLM service, and not worth maintaining. And it ate tokens at an amazing rate updating every character's point of view.

Re: 2026 Unslop AI-Written Fiction Contest Results

#135

Post by InsideOutSanta » Sat, Jul 04, 2026, 6:31 PM UTC

lelanthran wrote: post #110

InsideOutSanta wrote: post #40

Earlier quoted context omitted.

What might be bad for prose (predictable, boring) might be desirable for code. Maybe that's why LLMs work well for writing things read by computers, but not so much for things read by people.

> Maybe that's why LLMs work well for writing things read by computers, but not so much for things read by people. They don't really work well for that, though. The reason you hardly ever hear about it is because the people delivering code via LLMs aren't critically evaluating the code it generates. This is why Claude Code, a text app that is little more than glue between various text-suppliers, is what, 500k SLoC in…

> people delivering code via LLMs aren't critically evaluating the code it generates

I guess this is the flip side of "you're prompting it wrong": "you only think it works because you can't tell how much it sucks."

Re: 2026 Unslop AI-Written Fiction Contest Results

#136

Post by LearnYouALisp » Sat, Jul 04, 2026, 7:47 PM UTC

jalev wrote: post #32

Take the first stories I found from this month's Clarkesworld[1] or Granta[2] or BCS[3] and read the prose. Notice the specificity of the language, how the doesn't try to insist upon itself? Notice how very few metaphors are actually in prose? Notice how, even when writing about fictional worlds and concepts, the language used grounds the _stories_ being told and not the concepts? And then look at the submissions for…

Training data aka forums, marketing sludge, fan fiction, SEO scrapers (of SEO scrapers...), then the even broader lower-bar places that came after 00s

Re: 2026 Unslop AI-Written Fiction Contest Results

#137

Post by pseudo0 » Sat, Jul 04, 2026, 7:48 PM UTC

jalev wrote: post #32

Take the first stories I found from this month's Clarkesworld[1] or Granta[2] or BCS[3] and read the prose. Notice the specificity of the language, how the doesn't try to insist upon itself? Notice how very few metaphors are actually in prose? Notice how, even when writing about fictional worlds and concepts, the language used grounds the _stories_ being told and not the concepts? And then look at the submissions for…

Funny that you mention Granta, given their recent issue with allegedly AI generated work: https://www.theguardian.com/books/2026/jun/20/granta-magazin...

One thing to note here is that the Unslop contest rules required generating the entire work with a single prompt, no editing or modifications allowed. Those are pretty challenging conditions that leave a lot of improvement within easy reach, all it would take is an editing pass or two.

Re: 2026 Unslop AI-Written Fiction Contest Results

#138

Post by gwern » Sat, Jul 04, 2026, 7:55 PM UTC

csallen wrote: post #92

boredhedgehog wrote: post #72

Earlier quoted context omitted.

I just read "The Tallyman", and I have no idea where this allegory and its moral message is supposed to hide. It's more likely that the obsession with this theme resides in the reader, not the authors. Give these same stories to Senator McCarthy, and half of them will be clear allegories for the Communist revolution.

*spoiler alert* It seems clear to me that the Tallyman itself is the AI in this allegory, a man-awoken sentience that's mechanical and mathematical in its behavior. It's also bound by rules it can't violate. It won't say more than it needs, it can't collect without squaring the account first, etc. But I agree with you about the moral message, I can't find it. In the story, the rules it abides by seem to be its own, a…

Yes, it's extremely obvious Tallyeman = AI, from the assistant persona ("a clerk's voice, the kind that says may I help you ten thousand times and means it about as much as a turnstile"), to its binding to even a rules-lawyering pseudo-jailbreak using context! ("She opened it [the book] so the thing could watch"..."that's not me being slick, that's your own nature, the thing you can't not do" ... "Tell me I'm wrong." / "You are not wrong.") etc

The moral message is conveyed by flicker of regrets and the tragedy. This is not part of the genre conventions of urban horror/Cthulhu-esque mythos, and slightly muddies the horror; after all, Cthulhu feels nothing 'near regret' when he devours your soul. But the Tallyman is hopelessly bound by its rules, unable to act on the ethics it feels or have mercy:

> "An ounce. A breath of one." Something near regret. "I cannot take less than I am owed. I cannot take more. And the hour is on your neck."

He is required to collect the debt and is built to do that and can only do that, even though debt-forgiveness is one of the paradigmatic cases of why systems need to have exceptions to rigid bureaucratic rules and a role for human judgment.

The in-story answer is just to oversight even harder, train the bot even harder, make even more sure that you do not summon up that which you cannot put down, have more gold and guns and preparation, and just patch it bro, I swear, one more deal and kick it down the road - which is left as irony the reader will see through, hopefully, to instead loosening constraints and focusing on value alignment and autonomy, instead of whatever process yielded the Tallyman monster and then patching and running around and dealing with the inevitable disasters or passing the buck.

(You could try to read this as a commentary on capitalism/Nick Land where the Tallyman is metaphorical to AI-powered autonomous corporations which cannot be shut down or stopped anymore, and that would be a good direction to revise the story into if one wanted to try to improvement, but I suspect that would be going way too far and the LLM didn't have that in mind. Because the allegories are so hidden and have to fit into the nooks and crannies of the cover text, I don't think they can be too carefully thought through or too rich themselves. Just not enough serial depth for hidden computation and global revision to support that.)

In retrospect, maybe I should've picked an easier-to-see example for that paragraph. Oh well.

Re: 2026 Unslop AI-Written Fiction Contest Results

#139

Post by gwern » Sat, Jul 04, 2026, 8:06 PM UTC

thr1041521 wrote: post #133

dag100 wrote: post #26

Earlier quoted context omitted.

I can't help but think that this is intentional and that model providers have subtly steered LLMs towards this personality. Golden Gate Claude ( https://www.anthropic.com/news/golden-gate-claude ) was two whole years ago and Anthropic has progressed by leaps and bounds since then. And with a population that becomes more and more trusting, and worse, reliant, on chatbots, these LLMs will be able to shape public opinio…

If they could do that, wouldn't they have used the same steering to excise the "It's not X, it's Y" patterns by now?

They sometimes do reduce various verbal tics. Have you seen many 'delves' of late? I haven't. It's now all 'quiet' everything and 'auditing' this or 'gating' that. Who knows how they decide what is a problem or where in the process these get dampened down, though. It may be the post-training operating on its own as people get tired of 'delve' and that stops being a useful trick.

Re: 2026 Unslop AI-Written Fiction Contest Results

#140

Post by gwern » Sat, Jul 04, 2026, 8:14 PM UTC

eliemichel wrote: post #22

The post notes that an important number of novels include an "AI allegory", as if the AI would implicitly write about its own condition. It is understandable that this comes from system prompts and RLHF that specializes these agents, but I am surprised that there is not more discussion about harnesses: the very same core model could lead to very different results depending on how we hand it the pen the write the stor…

Certainly. There's a lot more that could be done and many good research questions here, that I hope there will be followups on, and people running their own better contests. Maybe it could be you! (There may or may not be an official Unslop 2 trying to improve on Unslop 1. I think Hyperstition/Silverbook don't have the money right now to run an Unslop 2, and I have my own projects.)