GPTZero launches 4o detector with 1/10,402 false positive rate, robust to paraphrasing attacks

sethlazar · x · 2026-09-25

AI detection startup GPTZero has launched GPTZero 4o, an all-purpose AI text detection model it says achieves a false positive rate of 1/10,402 on benchmarks and is its most robust model yet against edits and paraphrasing attacks used to evade detection. Cornell professor Seth Lazar welcomed the competition, saying academic editing needs all the help it can get against the advancing tide of AI-generated slop.

Original post →

More from Models

Models channel →