<?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>溯源 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%BA%AF%E6%BA%90/</link><description>Recent content in 溯源 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>Wed, 24 Jun 2026 16:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%BA%AF%E6%BA%90/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM 水印技术指南：AI 生成内容的溯源</title><link>https://guijiagi.com/posts/llm-watermark-guide/</link><pubDate>Wed, 24 Jun 2026 16:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/llm-watermark-guide/</guid><description>深入解析 LLM 文本水印技术原理、Kirchenbauer 方案、检测方法与鲁棒性挑战</description></item></channel></rss>