How does Pangram work? - Pangram
substack.com · 1,204 words · saved by 1 readers
The way that we tell the difference
We think it is important to be able to reliably identify AI-generated writing, so we built a detector that does it. Because the problem is so important, it’s only prudent to be transparent about how that works. When any author writes a sentence, they’re making thousands of conscious and unconscious decisions about how it should be composed. Fundamentally, AI detection is a problem of author identification – categorizing which decisions are prototypical of what kind of author. We can do this because, while LLMs like ChatGPT aren’t human, they are still a single author making decisions. The…
saved by
related reading
- How does Pangram work?pangram.substack.com
- I don't care (anymore) if your writing got a Pangram false positiveandrewwu.substack.com
- Seeing in Pangram Space | Pangrampangram.com
- Pangram 4 Technical Overviewpangram.com
- Pangram 4 Technical Reportpangram-public.s3.us-east-1.amazonaws.com
- I Wouldn't Say Pangram is Broken, But I Would Say That It's Brittlesubstack.com
- Why Perplexity and Burstiness Fail to Detect AI | Pangram Labspangram.com
- Does Pangram Work on Claude Fable 5? | Pangram Labspangram.com
- Employee Spotlight: Meet Katherine, AI Research Scientist | Pangram Labspangram.com
- If you let AI do your writing, I will come to your house and kill yousamkriss.substack.com
- How to Tell if Something is AI-Writtenhollisrobbinsanecdotal.substack.com
- We Can't Let AI Writing Take Over the Internetderekthompson.org