<?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>行为代理 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E8%A1%8C%E4%B8%BA%E4%BB%A3%E7%90%86/</link><description>Recent content in 行为代理 on AI 实战派 · 从技术到赚钱</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>Tue, 20 Oct 2026 13:48:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E8%A1%8C%E4%B8%BA%E4%BB%A3%E7%90%86/index.xml" rel="self" type="application/rss+xml"/><item><title>AGI 评测的哲学缺陷：行为代理为什么测不到主体</title><link>https://guijiagi.com/posts/2026-10-20-18-agi-evaluation-proxy-philosophical-gap/</link><pubDate>Tue, 20 Oct 2026 13:48:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-20-18-agi-evaluation-proxy-philosophical-gap/</guid><description>所有评测都用外部行为代理内部能力，当对象接近主体，代理与被代理之间的缝隙成为哲学缺陷</description></item></channel></rss>