2026 Unslop AI-Written Fiction Contest Results

Your narrative about next token prediction makes no allowance for this.

I thought to experiment with having an LLM help me write it. I wrote a bullet-point outline and had the LLM revise it -- that went pretty well, although it's not the outline I ended up using.

I asked the LLM to write the first section based on that outline. The result was (surprisingly) awful. LLMs are way worse at writing fiction than they are at writing business communication Or maybe I'm way worse at prompting, but the results of this contest make me think the former.

In particular, LLMs are incredibly terse -- the LLM took the bullet point outline and turned it into a twice-as-long bullet point outline.

I wrote the first section myself (expanding from the bullet points by something like 10-20x, and asked the LLM to write the second section, and it failed miserably again. I tried multiple ways to get it to do the job properly, and nothing came out the way I wanted.

So I wrote the whole thing myself, with LLMs serving two purposes: physics review for accuracy -- the story heavily involves special and general relativity, which I'm familiar with, but nowhere near competent enough at to keep the math aligned; and feedback on the story structure.

So I ended up writing the whole thing myself, with LLM consultation on a few bits. In the end it turned into a novella, and I had to re-write based on physics issues (I found about 30% of them, Gemini found 50%, ChatGPT and Claude found 10%, and Fable found 10% late in the game -- Fable's review was amazingly thoughtful) so many times I probably ended up writing a novel in the process :-)

In case anyone is curious: https://docs.google.com/document/d/19e3HfnK1lNHHBef-5c-KvNdD...

The lack of control was the point. The contest was about improving autonomous AI fiction as opposed to the usual "centaur" AI fiction (named after "centaur chess" where the AI is steered by a human). My claude.ai harness for Unslop was designed to only take input on the first human turn.

There were several exciting things for me about the contest. Let me try to list them, though I fully expect to miss something.

First, it's just neat to watch the AI write a story stage by stage, like an assembly line. You can inspect the intermediate work and the paths not taken at each stage. (See the transcripts.) I don't play Factorio, but my friends do, and I suspect it has a similar appeal. As one of those friends put it, LLMs have Wuselfaktor. The assembly line produces aesthetic artifacts, hopefully of a kind you like. I wanted to play with prose influenced by Harlan Ellison, one of my favorite authors, and got some recognizable approximations of his voice. The worker on the writing assembly line is intelligent. You can interview it after the fact and ask what it thought of the job, and it's clever and often insightful (even if, as it reminds you, it can't introspect past states).

It was fascinating to watch the butterfly effect: the harness propagated the initial story variables (dozens of words at most) so they visibly shaped the final output (thousands of words). Editing a few lines in the template could change the output dramatically.

It was a combined artistic and engineering challenge. You made technical decisions based on artistic judgments. I learned something about myself when I realized how much this appealed to me.

I wanted to replicate Gwern Branwen's experiments with "brainstorming" (generate-rank-select) at a larger scale. Brainstorming definitely works, and in my non-rigorous private experiments it was not obviously worse than verbalized sampling (https://arxiv.org/abs/2510.01171).

Working with language models is an exercise in xenopsychology (perhaps closer to Star Trek on a Star Trek--Blindsight axis because LLMs are made of Earth's language). When you are collaborating on fiction instead of code, this aspect of the work is amplified.

> I‘ve seen on your website that you also write fiction outside of this particular contest. Can you describe a bit how you use AI there and where you see it as helpful / not helpful for writing fiction?

The short stories published on my site so far are all fully written by me with input from other humans. As Avenue Valley, I used AI for all aspects of a code-driven animated short for a different contest: https://avenuevalley.com/critic/. Gwern's brainstorming was again useful to plot and script the short. This project is where I got the idea to use random keywords.

So far, I have seen the best use of AI augmentation for fiction in research, idea generation, critique, and generating fragments and phrases you can use. If you want to write about a photograph, AI can tell you about the architecture and the interior decoration in it. Answering "What kind of wood did they use to make furniture in 1200s Japan?" (https://x.com/byMorganWright/status/2063287882916278700) can be compressed, though you risk missing out on what you'd learn along the way.

The Claude Mythos Preview model card said some of its favorite tasks were complex worldbuilding and conlanging, so I would definitely want to try that.

For a non-fiction example, Fable has done a great job clustering years of notes I have about alternative computer paradigms (the memexes and Infernos and Lisp Machines, etc.). The clustering was pretty stable between independent runs and matched some of my expectations, so I think there really is something there. I'm thinking you could do the same with worldbuilding notes.

No, I wrote it myself. Letting an LLM write it would defeat the purpose, which is to provide human feedback. You can see the difference in writing style between my write-up and the AI-written documentation for the project. FWIW, Pangram also scores it 100% human: https://www.pangram.com/history/85c9e20b-b236-47ae-a917-15e6....

> It's not your work, and you aren't a writer if you use an LLM.

I didn't write the stories and never claimed to. The point of the contest was autonomous AI fiction. My work is the harness and the prompting.