Show HN: Training a model to identify AI web content from structure alone
Hey HN! We’re Vincent and Jochen from Sitefire (https://sitefire.ai). We have been working together for years, with backgrounds in RL/optimization at Stanford and software engineering from Technical University Munich (TUM).With Sitefire (YC W26), we help marketing teams get recommended by AI Search (ChatGPT, Google AI Overviews, AI Mode, Claude, etc.). Our software monitors prompts, sees which web pages get cited, and uses these insights to help marketing teams take action, e.g. create YouTube videos or write the right blog posts.This means we have a commercial stake in AI-generated web content. And for now, high-information, AI-generated content works great to get cited and recommended in AI Search.But after talking to hundreds of marketing teams, it became clear that everyone despises AI-generated content (“AI slop”). And yet, everyone still wants to leverage AI to create content. So we asked ourselves: what characterizes AI slop? Can we train a model to identify it from human-generated web pages?Researchers from the University of Maryland and Google DeepMind already asked this question for fiction. Their paper StoryScope (Russell et al., 2026) showed that you can tell AI-written stories from human ones by their structure alone, without looking at the words.We ported their pipeline to commercial web pages. Using the Wayback Machine, we collected 2,250 blog posts from 268 B2B company websites that were written before ChatGPT existed. For each blog post, five AI models (GPT-5.4, Claude Sonnet 4.6, Gemini 3 Flash, DeepSeek V3.2, Kimi K2.5) wrote their own version.Instead of looking at the words, we looked at how each post is built. We had an AI model answer 214 questions about every post, e.g. how hard it pushes its own product, whether it backs up its claims with sources, or whether it quotes a named expert. Then we trained a classifier on these answers.On blog posts it had never seen before, our classifier told AI-generated and human posts apart with 98% accuracy, getting only 19 of 1,740 wrong.Why does it work so well? Because all five AI models write in a similar shape. Mapping every AI model’s values for these features, we see they cluster together, while the human values sit apart and spread out much more. Of the 1% most unique blog posts in our data set, 149 are human, only 4 are AI.So what characterizes AI slop? It tells you the same thing three times. The title already promises what you'll get ("How to Cut Onboarding Time in Half"), the intro lays out what's coming, and the ending says it all again. 77% of the AI posts end by repeating their main point, compared to only 12% of the human posts. We call it the tidy, self-announcing blog post.Still, each AI model has its own accent. We trained a second classifier to tell which of the five AI models wrote a post, or whether a human did. It picks the right author 79% of the time, where random guessing (1 in 6) would get 17%. Almost all of its mistakes are mix-ups between the AI models, not between human and AI.The cool thing about structural features is that you can't simply reword your way out of it. We had each AI model rewrite its own posts until, on average, 73% of their original 13-word sequences were gone, and the AI slop classifier still worked just as well.We're building this into Sitefire: our agents get a structural understanding of text, so the posts they write go deeper and vary the way human writing does.There's a lot we haven't tested yet, like the myriad of humanizer tools, human rewriting, restructuring a post, or prompting an AI model to explicitly avoid these habits. And our human posts are mostly from 2020 to 2022, while the AI posts were generated in August 2026. Structure can't really tell when a human post was written, but it's still not a same-year comparison.We published the study with all the figures on arXiv: https://arxiv.org/abs/2609.15369. The code is on GitHub: https://github.com/pulse-energy-eu/slopshapeWe're pretty sure your own blog isn't AI slop, is it? We built a checker that runs one of your posts through the ten features from the paper, so you can see for yourself (the full report asks for a work email): https://sitefire.ai/slop-checker.Think you can tell AI slop from human writing? We also made a little game to see if you can keep up with our model, which gets all five rounds right: https://sitefire.ai/spot-the-slop.
16 points by jochenmadler - 4 comments
The limitation you flag at the end might be bigger than it looks. Human posts are 2020–2022, AI mirrors are August 2026, so the classifier has two things it could be keying on: AI-ness, or era. The tidy, self-announcing shape is also roughly where commercial blog writing drifted over those four years, partly because people have been reading AI output and copying it. The hard case is a 2026 human marketing post written by someone who's spent two years around these tools, and that case isn't in the set. Is there enough post-2023 human content in the Wayback data to build even a small holdout of it? Even a few hundred would tell you whether you're detecting the model or the decade.
The other thing worth stating explicitly is the base rate. 98% on a balanced holdout is great. Run it across a site that's 95% human and the same false positive rate starts producing a steady trickle of accusations, and the cost isn't symmetric: telling a real writer their work looks machine-generated is worse than letting an AI post through. Might be worth publishing the precision at a few realistic prevalences so people using it know what they're getting.
Of course, it's impossible to know for sure what was LLM processed or not, but some of your posts (like this one) have been getting classified that way.