JB

JB

@jasonbotterill · Twitter ·

independent findings reveal a photo of this man was found in every single pod the agents broke into. nobody at any lab knows who he is.

METR

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.

Quoted post media
Post media