arXiv AI-paper detector achieves 0.005% false positive rate on pre-2022 papers
danish037 · x · 2026-10-20
Responding to third-party vibechecks, the developer of a new arXiv AI-content detector confirmed it is deliberately conservative: with a strict threshold it achieves a 0.005% FPR on pre-2022 arXiv content to avoid flagging human-written papers. Commenters note that while AI detectors are unpopular, they're becoming necessary given the deluge of AI-generated papers — though humans remain the second line of defense.
More from Safety
- Microsoft says AI agents should be treated like insider threats as 'frontier models can't be trusted' — TechCrunch AI · 2026-10-20
- Studios Want AI to Mint New Franchises, but Pure AI Content Can't Be Copyrighted — WhatTheLJW · 2026-10-20
- French AI-generated novel axed from Goncourt longlist; writers demand AI text watermarking — zetalyrae · 2026-10-20
- NYC to take 15% of QFab IP proceeds and three board seats in landmark startup deal — MJBiercuk · 2026-10-20
- Fake Anthropic employee accounts run a novel X follow-based phishing scheme — edgarpavlovsky · 2026-10-20
- OSS Scanner's first scans report 77 critical and 803 high findings; LLMs now find 85% of CyberGym bugs — ClaudeDevs · 2026-10-20