Topic

#approval-fatigue

3 篇笔记

09-28

There are five words people throw around about agents right now. Context engineering, loop engineering, Jev engineering, harness engineering...

x.com· 16 分钟 ·#clippings·#AI·#agentic

08-25

从 Codex、Claude Code、Gemini CLI 到 OpenHands很多人讨论 AI Agent 安全时，关注的是：“模型会不会执行危险命令？”但真正重要的问题其实是：即使 Agent 决定执行危险命令，底层系统是否允许它成功？这就是 Sandbox（沙箱）存在的...

x.com· 9 分钟 ·#clippings·#agentic·#ai-safety

08-15

Your agent says the job is done and the tests never ran. It's sharp for twenty minutes, then forgets a rule you gave it at the start. You re...

x.com· 11 分钟 ·#clippings·#agentic·#agent-harness