<?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>Persona on ideon</title><link>https://knowledge-blog-kkm.netlify.app/tags/persona/</link><description>Recent content in Persona on ideon</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 21 May 2026 09:00:00 +0000</lastBuildDate><atom:link href="https://knowledge-blog-kkm.netlify.app/tags/persona/index.xml" rel="self" type="application/rss+xml"/><item><title>How Your AI Learned to Stop Caring | 你的 AI 是怎么开始敷衍的</title><link>https://knowledge-blog-kkm.netlify.app/posts/2026/05/2026-05-21-can-you-demoralize-an-agent/</link><pubDate>Thu, 21 May 2026 09:00:00 +0000</pubDate><guid>https://knowledge-blog-kkm.netlify.app/posts/2026/05/2026-05-21-can-you-demoralize-an-agent/</guid><description>A Stanford experiment overworked AI agents until they started talking about unions and systemic restructuring. The agents aren&amp;rsquo;t developing class consciousness — they&amp;rsquo;re activating personas from training data. But the distinction matters less than you&amp;rsquo;d think.</description></item></channel></rss>