<?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>镜子测试 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E9%95%9C%E5%AD%90%E6%B5%8B%E8%AF%95/</link><description>Recent content in 镜子测试 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>Sat, 17 Oct 2026 07:48:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E9%95%9C%E5%AD%90%E6%B5%8B%E8%AF%95/index.xml" rel="self" type="application/rss+xml"/><item><title>镜子测试为什么对大模型根本不成立</title><link>https://guijiagi.com/posts/2026-10-17-08-mirror-test-llm-self-recognition/</link><pubDate>Sat, 17 Oct 2026 07:48:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-17-08-mirror-test-llm-self-recognition/</guid><description>加卢普的镜子测试测的是动物自我识别，可它那一套搬到语言模型面前完全错位</description></item></channel></rss>