#49
2.1.248
Added --restricted (or CLAUDE_CODE_RESTRICTED=1 ): removes the built-in tools that run commands or code and WebFetch (unless named in --tools ), keeps file tools inside the working
推荐理由7 日窗口收录，分类页滚动库存。
AI 资讯
分类页是滚动库存，每页 24 条。首页只放当天精选。
Added --restricted (or CLAUDE_CODE_RESTRICTED=1 ): removes the built-in tools that run commands or code and WebFetch (unless named in --tools ), keeps file tools inside the working
Evaluating AI agents that use external tools requires realistic test scenarios that capture how practitioners compose tools and iterate across conversation turns. Constructing such
We've been shipping a lot of improvements to Claude Code based on your feedback. This week we made CLI startup faster, added more visibility into where your tokens go, made auto mo
You can now resume your terminal sessions in the Claude Code desktop app. Type /resume to pick any session you started from the CLI. The session continues in the app with the full
Breaking Claude Code Opus 5 Auto Mode Anthropic are putting a great deal of faith in Claude Code's auto mode for protecting their coding agent users against prompt injection attack
斯坦福大学研究人员领衔发布 Terminal-Bench-Science 0.1，用来自生命、物理、地球、数学和工程科学的 70 个专家精选任务评估 AI 智能体的科研能力。 🔗 阅读原文 via AIHOT · https://aihot.virxact.com/items/cmtcxdp3f07l3roq5uk6om1aw
斯坦福大学研究人员领衔发布 Terminal-Bench-Science 0.1，用来自生命、物理、地球、数学和工程科学的 70 个专家精选任务评估 AI 智能体的科研能力。
Warp 用人类反馈持续改进 Skill，为 Agent 建立了一套低摩擦的自我进化循环。