Julian Schrittwieser
@Mononofu
Member of Technical Staff at Anthropic
prev AlphaGo, AlphaZero, MuZero, AlphaProof, Gemini RL etc at Google DeepMind
가입 August 2007
128 팔로잉 중 32K 팬
If you only read one thing this week, make it the OpenAI incident investigation:
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.
더 보기
