Show HN: Training a model to identify AI web content from structure alone https://ift.tt/ed9O3CJ

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://ift.tt/nMXJipP . The code is on GitHub: https://ift.tt/GJwrNd6 We'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://ift.tt/V2x5NF7 . 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://ift.tt/FZ2reBp . https://ift.tt/nMXJipP September 22, 2026 at 06:30PM

Show HN: Notes on Agentic AI – A text-first guide for practicing engineers https://ift.tt/OzdkKsD

Show HN: Notes on Agentic AI – A text-first guide for practicing engineers https://ift.tt/kAuSmtN September 22, 2026 at 11:49PM

Show HN: Two unnecessary playgrounds – C# and ZX Spectrum in the browser https://ift.tt/7Imt6xF

Show HN: Two unnecessary playgrounds – C# and ZX Spectrum in the browser C# playground https://ift.tt/NrY1wHi ZX-Spectrum playground https://ift.tt/9LcxyaW September 22, 2026 at 12:52AM

Show HN: Viaduct – C4 models that coding agents can read and update https://ift.tt/VOUTreB

Show HN: Viaduct – C4 models that coding agents can read and update https://ift.tt/Wai85JG September 21, 2026 at 11:20PM

Show HN: Jev filters large HN discussions https://ift.tt/5R9y3uN

Show HN: Jev filters large HN discussions https://ift.tt/D4eOS9Z September 20, 2026 at 10:37PM

Show HN: KillSwitch – a programming language designed to be difficult for LLMs https://ift.tt/bmLro4R

Show HN: KillSwitch – a programming language designed to be difficult for LLMs https://ift.tt/hHcyxUA September 20, 2026 at 01:10AM

Show HN: CUA-S1 – A System One Model for Computer Use https://ift.tt/b6npMid

Show HN: CUA-S1 – A System One Model for Computer Use Hello HN! We're Dillon and Francesco from Cua. We were wondering how many computer use tasks actually need a full general purpose LLM (e.g. gpt-6-astra, claude-opus-5 etc.) to think through all their decisions and steps. Some tasks require thinking about a plan, exploring different paths, recovering from failure. Other tasks are a question of making local decisions, like this value should go in this box, or should I check this box, or this element should be ignored. We wondered how far we could go with a small model trained to only make these kinds of decisions. Our inspiration was Typesafe's Jev and its System One Model framing. This is a nod to the dichotomy between thinking quickly, automatically, and intuitively (system 1) vs. thinking slowly, analytically (system 2), as described by Daniel Kahneman. The interesting question for us was: what happens if you give a model an interface of current context, and a set of possible choices, and you ask it to return a probability for each choice? This kind of model does not generate output token by token like most LLMs do, but rather scores the options you give it, which you can check, trust, and use to drive your app's behavior. CUA-S1 is our answer for narrow, specialized decision models for computer use. Our first release is CUA-S1-FORMS. We built this from ideas and code in jevlike, and then trained a second model just to handle form interactions. It has 706k parameters, and the original checkpoint is 2.8 MB. The first training iteration took less than 30 minutes on synthetic data. Given a set of structured elements and values extracted from a document, it predicts whether to use the given value, CHECK, CLICK, or SKIP for each element. It does not predict new values for text fields, and does not consider screenshots. Element decisions are scored together, and your code can order the actions, and Cua Driver will execute them one at a time. A first evaluation of this specialist vs. hosted Jev on our form task: - For the whole decision set: 99.7% correct vs 83.6%. - For the subset of steps that require an action: 100% correct vs 96%. - For the subset of steps that are just leaving already-filled fields alone: 100% correct vs 74%. The specialist was trained specifically for this task and convention (just press skip for already filled boxes), while hosted Jev has not been fine-tuned for it, so this is an experiment in scoped specialization. We measured 7-9 ms to score a form locally vs. 260-280 ms per call to hosted Jev including network latency, though those samples measure different things and are not end-to-end form completion times. Our interest here is in the space between a brittle script and a general agent loop. The content and layout of form fields vary enough that scripts get unwieldy, but the set of available decisions can remain narrow and well scoped. We want to explore the possibility of a general agent encountering something novel, and passing well understood decisions over to specialists like this. That is a direction we are looking into. The current release is for forms only. We're open sourced the synthetic data generation, training, evaluation, and Driver integration under libs/cua-s1 with an MIT license. Comments welcome! Especially if you are building computer-use agents and have run into a recurring decision that is too variable to script but is too narrow to call another LLM for. https://ift.tt/FU8LfuZ September 19, 2026 at 09:22PM