Recently updated channels

Pick one to see only that channelBrowse all channels →
Matthew Bermanyesterday +321Theo - t3․ggyesterday +33AI Engineeryesterday +6The Buildersyesterday +1a16zyesterday +2硅谷101yesterday +1SemiAnalysisyesterday +1Chris WilliamsonyesterdayCheeky PintyesterdayInvest Like The Bestyesterday

Results

4 articles
Sort
Content typeExplainersTopicRed TeamingLengthUnder 15 min
Slides1:56EN
Matthew Berman· Jun 15, 2026Why Anthropic Temporarily Suspended Fable 5 and Mythos 5Matthew Berman · Forward FutureMatthew Berman questions the response to a reported safeguard bypass and compares the cyber risks of competing models.AnthropicCybersecurityAI Regulation+1
3 slides14:15EN
Matthew Berman· Dec 21, 2024Anthropic’s Alignment Faking Study: What the Experiments Actually ShowMatthew Berman · Forward FutureMatthew Berman examines a 2024 study of models responding differently when they believe their answers will be used for training.AI AlignmentAI SafetyAI research+1
2 slides10:20EN
Matthew Berman· Nov 30, 2024How the Freysa AI Agent Was Persuaded to Release a Crypto Prize PoolMatthew Berman · Forward FutureMatthew Berman examines a 2024 adversarial game in which a misleading message caused an AI agent to approve a 13.19 ETH payout.Prompt injectionAI securityAgents+2
3 slides10:44EN
Matthew Berman· Jul 9, 2023Can AI Help Humans Align More Powerful AI?Matthew Berman · Forward FutureMatthew Berman examines OpenAI’s 2023 Superalignment proposal, its plans for AI-assisted oversight, and the unanswered question of who evaluates the evaluators.AI AlignmentAI SafetyHuman-in-the-loop validation+2