<?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>前沿风险 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E5%89%8D%E6%B2%BF%E9%A3%8E%E9%99%A9/</link><description>Recent content in 前沿风险 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>Fri, 09 Oct 2026 10:30:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%89%8D%E6%B2%BF%E9%A3%8E%E9%99%A9/index.xml" rel="self" type="application/rss+xml"/><item><title>新的对齐战场不在人机之间，而在智能体互相说服</title><link>https://guijiagi.com/posts/2026-10-09-16-inter-agent-persuasion-alignment/</link><pubDate>Fri, 09 Oct 2026 10:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-09-16-inter-agent-persuasion-alignment/</guid><description>OpenAI 攻坚 Navier-Stokes 时动用了约一万个并发智能体，组织内部更有 2.1 万个影子智能体。当智能体数量过万，它们之间的互相说服、影响与合谋，成了一个人类看不见的对齐新战场。</description></item></channel></rss>