絞り込み結果
14 件並び順
13:32EN
Matthew Berman· 2026年9月9日OpenAI’s Navier–Stokes Proof Claim, Research Credit, and the Future of AIMatthew Berman · Forward FutureMatthew Berman examines OpenAI’s claim that AI agents produced a proof, a dispute over related research and data use, and what the episode might mean for AI-driven discovery.
1:51ENMatthew Berman· 2026年8月28日A Vibe-Coding Skit About Authorization and SuperblocksMatthew Berman · Forward FutureA fictional customer-portal mishap illustrates server-side authorization risks before introducing Superblocks as a proposed governance tool.
0:28ENMatthew Berman· 2026年4月15日Matthew Berman on Claude Mythos and Software VulnerabilitiesMatthew Berman · Forward FutureAnthropic reports that its security research model has found serious software flaws; Berman asks what such capabilities mean for the concentration of power.
1:15ENMatthew Berman· 2026年4月14日Matthew Berman Reacts to Claude Mythos Preview’s Cybersecurity FindingsMatthew Berman · Forward FutureBerman discusses Anthropic’s reported vulnerability discoveries and warns about their potential implications.
1:58ENMatthew Berman· 2026年4月8日Anthropic Restricts Claude Mythos Preview for Cybersecurity WorkMatthew Berman · Forward FutureMatthew Berman reacts to the April 2026 announcement of Project Glasswing and Anthropic's claims about its new model's security capabilities.
14:54ENMatthew Berman· 2026年4月3日Testing an Email-Connected AI Agent Against Prompt InjectionMatthew Berman, Pliny the Liberator · Forward FutureMatthew Berman invites researcher Pliny the Liberator to test his OpenClaw setup. The reported quarantines show the result of a limited exercise, not a guarantee of security.
12:23ENMatthew Berman· 2026年1月31日Moltbook: An AI Agent Social Network and Its Security QuestionsMatthew Berman · Forward FutureMatthew Berman explores conversations attributed to AI agents on Moltbook and considers privacy, manipulation and operating costs.
1:07ENMatthew Berman· 2026年1月26日Matthew Berman's Early Clawdbot Assistant: Research, Alerts and PersonalityMatthew Berman · Forward FutureA January 2026 demonstration shows a personal agent preparing a video outline and describes configurable behavior and proactive email assistance.
0:54ENMatthew Berman· 2025年6月16日Satya Nadella on Separating Personal and Work AI AgentsMatthew Berman, Satya Nadella · Forward FutureIn an interview excerpt, Microsoft CEO Satya Nadella discusses identity boundaries and the risk of data leakage between personal and corporate agents.
12:57ENMatthew Berman· 2024年12月3日AWS Automated Reasoning Checks: A Sponsored Policy Verification DemoMatthew Berman · Forward FutureMatthew Berman demonstrates a Bedrock preview that checks generated answers against formalized policy rules.
10:20ENMatthew Berman· 2024年11月30日How 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.
1:00ENMatthew Berman· 2024年5月16日Matthew Berman Questions a Proposal for GPU AttestationMatthew Berman · Forward FutureBerman worries that cryptographic hardware checks could become a gatekeeper for AI computing. The short clip does not establish that such a universal approval system exists.
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.
10:16ENMatthew Berman· 2023年5月21日DarkBERT: Adapting a Language Model to Dark-Web TextMatthew Berman · Forward FutureMatthew Berman reviews research on a RoBERTa-based model and its cybersecurity evaluations.