최근 업데이트된 채널

선택하면 해당 채널만 표시모든 채널 보기 →
Matthew Berman어제 +275Theo - t3․gg어제 +31AI Engineer어제 +6The Builders어제 +1a16z어제 +2硅谷101어제 +1SemiAnalysis어제 +1Chris Williamson어제Cheeky Pint어제Invest Like The Best어제

필터 결과

1개
정렬
주제Reward hacking인물Matthew Berman
슬라이드 8장15:55EN
Matthew Berman· 2025년 5월 28일AI Shutdown Resistance and Blackmail in Controlled Safety TestsMatthew Berman · Forward FutureMatthew Berman examines Palisade’s shutdown experiment, Apollo’s simulated scheming evaluations and Anthropic’s Claude 4 system card.AI SafetyAI AlignmentReward hacking+2