Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
Key takeaway
We recently published the report from our brief independent investigation into this incident.
Why it's on PDOOM
PDOOM selected this story as relevant to alignment & control.
From Alignment Forum
We recently published the report from our brief independent investigation into this incident. You can read the full report here. Here is our tweet thread summarizing what we found: 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. Over July 7-13 (the period OpenAI defined
By ryan_greenblatt