Recently updated channels

Pick one to see only that channelBrowse all channels →
Matthew Bermanyesterday +231AI Engineeryesterday +6Theo - t3․ggyesterday +11The Buildersyesterday +1a16zyesterday +2硅谷101yesterday +1SemiAnalysisyesterday +1Chris WilliamsonyesterdayCheeky PintyesterdayInvest Like The Bestyesterday

Results

5 articles
Sort
TopicAgent red teamingPersonMatthew BermanSpeakersSolo
8 slides15:55EN
Matthew Berman· May 28, 2025AI 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
3 slides9:00EN
Matthew Berman· Dec 20, 2024Best-of-N Jailbreaking: What Repeated Prompt Variations Revealed in 2024Matthew Berman · Forward FutureMatthew Berman reviews research on how repeated input variations can expose safety failures in text, vision and audio models.Agent red teamingAI SafetyMultimodal AI+2
0:59EN
Matthew Berman· Apr 10, 2024Anthropic’s Many-Shot Jailbreaking ResearchMatthew Berman · Forward FutureMatthew Berman explains a 2024 study on how long sequences of examples can make some language models more likely to bypass safety safeguards.Agent red teamingAI SafetyContext engineering
3 slides18:47EN
Matthew Berman· Apr 7, 2024What Anthropic’s Many-Shot Jailbreaking Research FoundMatthew Berman · Forward FutureMatthew Berman reviews a 2024 study of long-context safety failures and the limits of its tested mitigations.AI SafetyAgent red teamingContext engineering+1
4 slides19:59EN
Matthew Berman· Mar 12, 2024Testing Model Responses to Masked Harmful RequestsMatthew Berman · Forward FutureMatthew Berman compares refusals, decoding errors and inconsistent responses in informal 2024 experiments across several language models.AI SafetyAgent red teamingSecurity & safety+1