Recently updated channels

Pick one to see only that channelBrowse all channels →
Matthew Bermantoday +20AI Engineertoday +8The Builderstoday +1Theo - t3․ggyesterday +115a16zyesterday +1Reid Hoffmanyesterday +1Chris Williamsonyesterday +1Conversations with TyleryesterdayCitadel Securities2 days ago +1硅谷1012 days ago +1

Results

1 articles
Sort
TopicReinforcement LearningPersonTheo Browne
7 slides34:23EN
Theo - t3․gg· Sep 1, 2026How 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