絞り込み結果
7 件並び順
25:34EN
Matthew Berman· 2026年7月8日Anthropic’s J-Space Research: What Its Experiments Reveal and What Remains UnknownMatthew Berman · Forward FutureMatthew Berman examines experiments on internal representations in Claude, from causal interventions to safety auditing and the limits of consciousness claims.
1:53ENMatthew Berman· 2026年7月8日What Anthropic’s J-Space Research Suggests About AI ReasoningMatthew Berman · Forward FutureMatthew Berman discusses internal model representations, interventions and the question of consciousness, while the research itself describes important limits.
18:07ENMatthew Berman· 2026年4月16日Claude Opus 4.7: Benchmarks, Cyber Safeguards and Open QuestionsMatthew Berman · Forward FutureMatthew Berman compares Anthropic’s April 2026 Opus release with the limited Mythos Preview and examines its system card.
1:56ENMatthew Berman· 2025年11月10日Can a Language Model Detect an Injected Concept?Matthew Berman · Forward FutureMatthew Berman discusses an Anthropic experiment in which models sometimes report an artificial change to their internal activations.
15:35ENMatthew Berman· 2025年5月24日Claude 4 Reactions: Safety Tests, Model Welfare and CodingMatthew Berman · Forward FutureMatthew Berman reviews early reactions to Anthropic’s May 2025 Claude 4 release, from simulated whistleblowing to coding demonstrations and model-welfare research.
21:13ENMatthew Berman· 2024年6月6日AI Workers’ Right to Warn and the Debate Over AGI SafetyMatthew Berman · Forward FutureMatthew Berman examines a 2024 open letter on speaking up about AI risks alongside predictions from former OpenAI employees Leopold Aschenbrenner and Daniel Kokotajlo.
4:48ENMatthew Berman· 2023年7月12日PoisonGPT: A Demonstration of Model Supply-Chain RiskMatthew Berman · Forward FutureMatthew Berman discusses Mithril Security’s 2023 demonstration of an edited GPT-J model and a misleading repository name. The experiment illustrates a supply-chain risk, not a breach of the original model provider.