what kind of incentive structures existed around the LLM agents deployed to help you in the investigation? i'm thinking through the game theory here, and wondering if willingness-to-participate is even adaptive tbh
I was the main person doing transcript analysis for this investigation of the Hugging Face incident. My main takeaway: We don't have good approaches for understanding/overseeing the activity and aims of AI 'swarms'. I semi-jokingly called our efforts a "slop-vestigation" becauseMETR & 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.- what kind of incentive structures existed around the LLM agents deployed to help you in the investigation? i'm thinking through the game theory here, and wondering if willingness-to-participate is even adaptive tbh
