<?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>AI反馈 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/ai%E5%8F%8D%E9%A6%88/</link><description>Recent content in AI反馈 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>Tue, 30 Jun 2026 11:25:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/ai%E5%8F%8D%E9%A6%88/index.xml" rel="self" type="application/rss+xml"/><item><title>AI对齐技术前沿：可扩展监督与AI反馈</title><link>https://guijiagi.com/posts/ai-alignment-frontier-scalable-oversight/</link><pubDate>Tue, 30 Jun 2026 11:25:00 +0800</pubDate><guid>https://guijiagi.com/posts/ai-alignment-frontier-scalable-oversight/</guid><description>深入探讨2026年AI对齐技术的前沿方向，包括可扩展监督、AI反馈（RLAIF）、辩论机制等，分析技术原理与实践挑战</description></item></channel></rss>