Frontier models can unmask authorship from a single text, no tools needed

MohitIyyer · x · 2026-11-20

New research thread from atreydesai: given a single text, frontier models can often tell whether AI wrote it, which lab's AI, or even the specific human behind it—no web search, no tools, no candidate list. MohitIyyer notes authorship attribution is advancing extremely fast, with major deanonymization and impersonation risk.

Original post →

More from Models

Models channel →