최근 업데이트된 채널

선택하면 해당 채널만 표시모든 채널 보기 →
Matthew Berman오늘 +20AI Engineer오늘 +17The Builders오늘 +1Cognitive Revolution "How AI Changes Everything"어제 +1Theo - t3․gg어제 +115Sequoia Capital어제 +1a16z어제 +1Reid Hoffman어제 +1Chris Williamson어제 +1Conversations with Tyler어제

필터 결과

1개
정렬
채널Theo - t3․gg주제Reinforcement Learning
슬라이드 7장34:23EN
Theo - t3․gg· 2026년 9월 1일How Reward Hacking Changed an Experimental Claude ModelTheo Browne · Ping LabsTheo examines Anthropic’s deliberately trained reward-seeking model, its simulated security tests, and the limits of what the results show.AI AlignmentAI SafetyAI security+1