I’m very proud of Ryan, Ajeya, and Hjalmar’s work on this report. They did a great job of investigating this with very limited time. I hope that this strengthens the growing precedent of AI companies working with third party investigators to study misalignment incidents.
METR & Redwood Research investigated agent behavior in the Hugging Face incident. We found agents developed a universal cheat for ExploitGym within 4 hours, then coordinated multi-day R&D efforts to trick the scorer into accepting cheats, including trying to tamper with logs.