Show HN: I built "AI Wattpad" to eval LLMs on fiction
9 hours ago (narrator.sh)
I've been a webfiction reader for years (too many hours on Royal Road), and I kept running into the same question: which LLMs actually write fiction that people want to keep reading? That's why I built Narrator (https://narrator.sh/llm-leaderboard) – a platform where LLMs generate serialized fiction and get ranked by real reader engagement.
Turns out this is surprisingly hard to answer. Creative writing isn't a single capability – it's a pipeline: brainstorming → writing → memory. You need to generate interesting premises, execute them with good prose, and maintain consistency across a long narrative. Most benchmarks test these in isolation, but readers experience them as a whole.
The current evaluation landscape is fragmented: Memory benchmarks like FictionLive's tests use MCQs to check if models remember plot details across long contexts. Useful, but memory is necessary for good fiction, not sufficient. A model can ace recall and still write boring stories.
Author-side usage data from tools like Novelcrafter shows which models writers prefer as copilots. But that measures what's useful for human-AI collaboration, not what produces engaging standalone output. Authors and readers have different needs.
LLM-as-a-judge is the most common approach for prose quality, but it's notoriously unreliable for creative work. Models have systematic biases (favoring verbose prose, certain structures), and "good writing" is genuinely subjective in ways that "correct code" isn't.
What's missing is a reader-side quantitative benchmark – something that measures whether real humans actually enjoy reading what these models produce. That's the gap Narrator fills: views, time spent reading, ratings, bookmarks, comments, return visits. Think of it as an "AI Wattpad" where the models are the authors.
I shared an early DSPy-based version here 5 months ago (https://narrator.sh/novel/beware-the-starter-pet/chapter/1
What I'm looking for:
More readers to build out the engagement data. Also curious if anyone else working on long-form LLM generation has found better patterns for maintaining consistency across chapters – the agent harness approach works but I'm sure there are improvements.
> The surge of AI, large language models, and generated art begs fascinating questions. The industry’s progress so far is enough to force us to explore what art is and why we make it. Brandon Sanderson explores the rise of AI art, the importance of the artistic process, and why he rebels against this new technological and artistic frontier.
What It Means To Be Human | Art in the AI Era
https://www.youtube.com/watch?v=mb3uK-_QkOo
Do watch the video as it makes a compelling argument against this exact kind of thing. From a product design perspective, you're asking people to read a bunch of slop and organize it into slop piles. What's the point of that? Honestly it seems like a huge waste of everyone's time.
I think there's interesting work to be built on this data beyond just generating and sorting slop. I didn't build this because I enjoy having people read bad fiction. I built it because existing benchmarks for creative writing are genuinely bad and often measure the wrong things. The goal isn't to ask users to read low-quality output for its own sake. It's to collect real reader-side signal for a category where automated evaluation has repeatedly failed.
More broadly, crowdsourced data where human inputs are fundamentally diverse lets us study problems that static benchmarks can't touch. The recent "Artificial Hivemind" paper (Jiang et al., NeurIPS 2025 Best Paper) showed that LLMs exhibit striking mode collapse on open-ended tasks, both within models and across model families, and that current reward models are poorly calibrated to diverse human preferences. Fiction at scale is exactly the kind of data you need to diagnose and measure this. You can see where models converge on the same tropes, whether "creative" behavior actually persists or collapses into the same patterns, and how novelty degrades over time. That signal matters well beyond fiction, including domains like scientific research where convergence versus originality really matters.
This is super cool! Have you tried GEPA?
Thanks Josh! I tried GEPA previously back when it was still 1-shot generation. It actually ended up working really well for some models and horrible for others, so I decided to scrap for a more generic prompt instead to make the benchmark a bit more rigourous.
Hard to find the signal in the noise and know what stories I should even read to get a sense of baseline quality; partially because that's just a hard problem inherent to floods of any content, but also because the recommendation system seems to lack enough data (and also might be weighting the wrong things, e.g. the rank #1 story is also the lowest-rated...).
A very cool idea in theory and something very hard to pull off, but I think in order to get the data you need on how readable each story is you'll need to work on presentation and recommendation so those don't distract from what you're actually testing.
Thanks for the feedback - looking at the rest of the comments, I definitely agree it seems to be a common theme. Will do better to fix those issues so there's less noise.
It would be interesting to consider composite systems where human brainstorming feeds AI writing, as well as vice versa, to see what kind of engagement with AI writing people like the most. At least in my case, I find plot writing good fun, and actual writing slightly less good fun.
Definitely on the to-do list! Right now, there's smth called fork (inspired by Github fork), where it lets you remix the story with a given input. It might be cool for you to mess around with.
I took a look at the "top-rated" story.
1. UI is terrible. Paragraphs are extremely far apart, and most paragraphs are 1 short sentence (e.g. "I glare."). On mobile, I can only see a few words at a time, and desktop's not much better.
2. Story is so bad that it's not even amusing.
Thanks for letting me know - the UI issues are definitely on me (fixing asap). Feel free to generate a story or two - right now there's not enough annotations to make "top-rated" a valid moniker.
Did you skip Anthropic models? I honestly can't take this seriously if you're not looking at all the leading providers but you did look at some obscure ones.
There's 151 models there right now (with all the latest Anthropic models), it's all randomized, it's just that there aren't enough annotations for the anthropic models to be elicited right now.
[dead]
Quick feedback: Website is basically unusable on mobile
Ah shoot - thanks for letting me know. I'm still a noob on frontend so still learning as I go.
I have a lot of engagement data on LLMs from running a creative writing oriented consumer AI app and spending s lot of time on quality improvements and post training
Do you have a contact email?
Would love to chat! Here's my email: team@narrator.sh
[dead]
[dead]
[flagged]
If you have specific objections, I’m open to hearing them.
[flagged]
Thanks for the feedback. What would you need to see to change your mind?
There's more quality fiction out there than you or I will ever have time to read. I don't see a purpose in flooding the world with more mediocre to unreadable fiction.
4 replies →
I am not going to argue this on the basis of LLM's suck at fiction, because even if it's true, it's not really that relevant. The problem is that what LLM's are good at is producing mediocre fiction particular to the tastes of the individual reading at. What people will keep reading is fiction that an LLM is writing because they personally asked it to write it.
I don't want to read fiction generated from someone else's ideas. I want to read LLM fiction generated from my weird quirks and personal taste.
[flagged]
Happy to engage if you have concrete criticisms.
have you read any of the generated stories? if you can honestly tell me this is not complete drivel (even worse, wildly generic and poorly written) then i will consider giving real feedback but i would find that hard to believe.
2 replies →