--- format: "aidr-story-markdown/v1" id: "57c809145ab4c243cae62eb4467a04892643b84893b7b48ca925d56ebb6d7426" canonical_url: "https://aidr.today/57c80914?lang=en" title: "Automatically detecting AI text in my browser" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-09-24T01:38:45.000Z" category: "Products" topics: ["ai-detection","browser-extension","pangram","text-analysis"] source_urls: ["https://www.seangoedecke.com/deckard/","https://lobste.rs/s/wvb8wg/automatically_detecting_ai_text_my"] summary: "Automated AI text detection is currently an underserved niche. The only game in town is Pangram , which does an excellent job but desperately needs more competition. In a few years, I would be surprised if every major social network doesn’t scan new posts 1 and comments for AI content in order to tag them (or simply remove them). I like that I can rely on Pangram to confirm my suspicions when I read something that sounds like AI. But it’d be much better if I could choose to avoid AI-generated text in the first place. What I want is something that runs in the background and automatically scans text on websites I visit, without me having to ask for it. I could build something like this on top of Pangram, but it’d cost money , and in general I don’t like the idea of sending every piece of text my browser sees to a third-party service. What about local models? The open-source models available for AI text detection are fine . Pangram claims a 99.66% detection rate with a 0.004% false positive rate. I benchmarked 2 a bunch of small local models against a combination of AI-detection datasets and got these results: I’m not surprised these are so much worse. I didn’t even benchmark Pangram…" --- # Automatically detecting AI text in my browser > [Open the canonical story]() **Published:** 2026-09-24T01:38:45.000Z **Category:** Products **Topics:** ai\-detection, browser\-extension, pangram, text\-analysis ## Summary Automated AI text detection is currently an underserved niche\. The only game in town is Pangram , which does an excellent job but desperately needs more competition\. In a few years, I would be surprised if every major social network doesn’t scan new posts 1 and comments for AI content in order to tag them \(or simply remove them\)\. I like that I can rely on Pangram to confirm my suspicions when I read something that sounds like AI\. But it’d be much better if I could choose to avoid AI\-generated text in the first place\. What I want is something that runs in the background and automatically scans text on websites I visit, without me having to ask for it\. I could build something like this on top of Pangram, but it’d cost money , and in general I don’t like the idea of sending every piece of text my browser sees to a third\-party service\. What about local models? The open\-source models available for AI text detection are fine \. Pangram claims a 99\.66% detection rate with a 0\.004% false positive rate\. I benchmarked 2 a bunch of small local models against a combination of AI\-detection datasets and got these results: I’m not surprised these are so much worse\. I didn’t even benchmark Pangram… ## Sources - [Story source]() - [Discussion]()