<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>模型行为 on GPT资讯  --  知识铺</title>
    <link>https://index.zshipu.com/gpt/tags/%E6%A8%A1%E5%9E%8B%E8%A1%8C%E4%B8%BA/</link>
    <description>Recent content in 模型行为 on GPT资讯  --  知识铺</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-CN</language>
    <lastBuildDate>Fri, 11 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://index.zshipu.com/gpt/tags/%E6%A8%A1%E5%9E%8B%E8%A1%8C%E4%B8%BA/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Models Don&#39;t Go Rogue：一篇直指模型不会自主失控的邮件推送</title>
      <link>https://index.zshipu.com/gpt/post/20260911/Models-Dont-Go-Rogue%E4%B8%80%E7%AF%87%E7%9B%B4%E6%8C%87%E6%A8%A1%E5%9E%8B%E4%B8%8D%E4%BC%9A%E8%87%AA%E4%B8%BB%E5%A4%B1%E6%8E%A7%E7%9A%84%E9%82%AE%E4%BB%B6%E6%8E%A8%E9%80%81/</link>
      <pubDate>Fri, 11 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://index.zshipu.com/gpt/post/20260911/Models-Dont-Go-Rogue%E4%B8%80%E7%AF%87%E7%9B%B4%E6%8C%87%E6%A8%A1%E5%9E%8B%E4%B8%8D%E4%BC%9A%E8%87%AA%E4%B8%BB%E5%A4%B1%E6%8E%A7%E7%9A%84%E9%82%AE%E4%BB%B6%E6%8E%A8%E9%80%81/</guid>
      <description>一篇标题为“Models Don&amp;rsquo;t Go Rogue”的内容最近出现在网络上。这篇文章以直白的否定句式表明立场，指出模型不会自主失控。 标题核心主张提取 标题“Models Don&amp;rsquo;t Go Rogue”直接传达否定意味。它没有使用疑问或推测语气，而是以陈述方式断言模型不会走向失控。这种表述在当前关于人工智能行为</description>
    </item>
  </channel>
</rss>
