Recently updated channels

Pick one to see only that channelBrowse all channels →
AI Engineertoday +6Matthew Bermanyesterday +478Theo - t3․ggyesterday +52a16zyesterday +1The Buildersyesterday +1硅谷101yesterday +1SemiAnalysisyesterday +1Chris WilliamsonyesterdayCheeky PintyesterdayInvest Like The Bestyesterday

Results

1 articles
Sort
ChannelTheo - t3․ggTopicReinforcement LearningSpeakersSolo
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