絞り込み結果
5 件並び順
25:15EN
Matthew Berman· 2026年4月8日Matthew Berman on Claude Mythos, Project Glasswing and AI SecurityMatthew Berman · Forward FutureBerman examines Anthropic’s limited cybersecurity preview and its reported capabilities, then weighs the promise and risks of increasingly capable AI systems.
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.
40:00ENMatthew Berman· 2026年2月24日How Matthew Berman Built an OpenClaw Workflow for His TeamMatthew Berman · Forward FutureA tour of sponsorship triage, CRM, meeting notes, security, scheduling, memory and backup after a month of heavy use.
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.
12:17ENMatthew Berman· 2023年2月27日A 2023 Guide to Prompting ChatGPT: Instructions, Examples, and LimitationsMatthew Berman · Forward FutureMatthew Berman walks through prompt components, common tasks, examples, and adversarial prompting in an early ChatGPT tutorial.