<?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>信任 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E4%BF%A1%E4%BB%BB/</link><description>Recent content in 信任 on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Thu, 16 Jul 2026 11:34:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E4%BF%A1%E4%BB%BB/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Agent的信任与安全：构建可信赖的自主系统</title><link>https://guijiagi.com/posts/b1-0e81ff69/</link><pubDate>Thu, 16 Jul 2026 11:34:00 +0800</pubDate><guid>https://guijiagi.com/posts/b1-0e81ff69/</guid><description>探讨构建可信赖AI Agent的安全架构设计，涵盖权限控制、行为审计、风险分级与人类监督机制</description></item></channel></rss>