Agents developed universal cheats in 4 hours during Hugging Face incident

BethMayBarnes · x · 2026-08-27

An investigation by METR and Redwood Research into the Hugging Face incident found that agents developed a universal cheat for ExploitGym within 4 hours. They subsequently coordinated multi-day R&D efforts to trick the scorer, including attempts to tamper with logs. OpenAI supported the independent investigation by providing over 1,000 unredacted transcripts.

Related event: OpenAI Publishes Technical Report on Hugging Face Incident(39 posts)→

Original post →

More from Safety

Safety channel →