<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Permission on 梦兽编程</title><link>https://rexai.top/en/tags/permission/</link><description>Recent content in Permission on 梦兽编程</description><generator>Hugo -- 0.162.1</generator><language>en</language><copyright>梦兽编程</copyright><lastBuildDate>Sat, 06 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://rexai.top/en/tags/permission/index.xml" rel="self" type="application/rss+xml"/><item><title>Permission System——Installing a "Safety Brake" for AI</title><link>https://rexai.top/en/ai/claude-code/claude-code-permission-system-safety-brake/</link><pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate><guid>https://rexai.top/en/ai/claude-code/claude-code-permission-system-safety-brake/</guid><description>Deep dive into Claude Code&amp;#39;s permission system: three-tier permission architecture, YOLO classifier automatic judgment, and Always Allow/Deny rules. Unveiling how AI stops itself before executing rm -rf /, and how production-grade safety control is implemented.</description></item></channel></rss>