Study finds frontier models can identify AI or human authors from a single text
A new study shows frontier models like Claude can often tell from a single text whether it was AI-written, by which lab, or even by which human author, prompting jokes about automating peer-review signatures.
2026-11-20 ~ 2026-11-20 · 2 related posts
- Frontier models can unmask authorship from a single text, no tools needed — MohitIyyer · 2026-11-20
- Claude can identify which human wrote a text, and de-anonymization is progressing fast — najoungkim · 2026-11-20