<?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>对齐路线 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E5%AF%B9%E9%BD%90%E8%B7%AF%E7%BA%BF/</link><description>Recent content in 对齐路线 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>Sun, 18 Oct 2026 08:54:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%AF%B9%E9%BD%90%E8%B7%AF%E7%BA%BF/index.xml" rel="self" type="application/rss+xml"/><item><title>递归放大：用弱AI辅助训练强AI这条路通向对齐吗</title><link>https://guijiagi.com/posts/2026-10-18-19-ai-amplification-human-copilot/</link><pubDate>Sun, 18 Oct 2026 08:54:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-18-19-ai-amplification-human-copilot/</guid><description>AI放大设想让一个被对齐的弱模型辅助人类完成推理，再逐步放大这个对齐内核，避免直接造出未对齐的强系统，本文分析放大链如何保住对齐，又在哪里可能走样。</description></item></channel></rss>