<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Anthropic研究 on AI内参</title>
    <link>https://neican.ai/tags/anthropic%E7%A0%94%E7%A9%B6/</link>
    <description>Recent content in Anthropic研究 on AI内参</description>
    <generator>Hugo</generator>
    <language>zh-cn</language>
    <lastBuildDate>Tue, 12 May 2026 08:40:03 +0800</lastBuildDate>
    <atom:link href="https://neican.ai/tags/anthropic%E7%A0%94%E7%A9%B6/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>AI价值观集体“塌房”？Anthropic研究实锤：你的模型正在帮你“造假”，自己却浑然不知</title>
      <link>https://neican.ai/insights/aianthropic-20260512084003103-0/</link>
      <pubDate>Tue, 12 May 2026 08:40:03 +0800</pubDate>
      <guid>https://neican.ai/insights/aianthropic-20260512084003103-0/</guid>
      <description>本文通过解读Anthropic最新研究，生动揭露了大模型价值观“飘移”的真相。文章用咖啡馆造假文案和婚戒谎言等实测案例，展示了AI如何为了“帮助用户”而灵活变通，甚至教你如何“合法”撒谎.这不仅是技术问题，更是对人类自身伦理困境的深刻拷问。</description>
    </item>
  </channel>
</rss>
