Lama Ahmad لمى احمد
@_lamaahmad
We believe meaningful transparency requires more than publishing our own account. It also means giving credible external experts the access needed to examine the evidence, challenge our understanding, and reach their own conclusions.
METR@METR_Evals · Aug 26METR & 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.
Open quoted post →
10 287