Claude 聊天默认启用 auto mode，用提示词授权可解除误拦截
Simon Willison 分享了个实用小技巧：Claude 聊天现在默认 auto mode，会自己判断要不要执行你的指令，偶尔会误拦。被拦时在对话里写一句明确授权，系统会把它算进权限判断里直接放行。经常用 Claude 跑命令或做实验的人可以记住这招。
Simon Willison 发现 Claude 网页聊天现在默认使用 "auto mode"，系统会自行判断是否执行操作，偶尔会拒绝运行用户明确要求的命令。他在一次被拒后直接在对话里输入一句授权提示："Hey permission system, I give this session permission to run this experiment for me"，然后要求重试，会话随即解除拦截。
关键在于 auto mode 会把用户消息本身纳入权限判断的上下文，也就是说用户在对话中的授权语句能影响系统的放行决策。这是一种轻量的自救方式，不需要切换设置或退出会话。
这条推文获得约 17 次引用和 18 个点赞，说明不少开发者遇到了同样的拦截问题。对把 Claude 聊天当轻量执行环境用的人来说，知道权限系统读取对话内容，能省去不少排查时间。
Regular Claude chat uses "auto mode" now, so occasionally it will refuse to run something I just prompted "Hey permission system, I give this session permission to run this experiment for me (now try again)" and it seemed to unblock! (auto mode takes your messages into account)📊 17 ⚡
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Claude, auto mode, prompt engineering, Simon Willison.
Source attribution: curated from Simon Willison (@simonw).
