<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Ruozhiba on Margrop Blog</title>
    <link>https://blog.margrop.net/en/tag/ruozhiba/</link>
    <description>Recent content in Ruozhiba on Margrop Blog</description>
    <generator>Hugo</generator>
    <language>en-US</language>
    <lastBuildDate>Fri, 14 Aug 2026 13:10:00 +0800</lastBuildDate>
    <atom:link href="https://blog.margrop.net/en/tag/ruozhiba/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Is Peeking at Your Opponent&#39;s Chessboard Immoral? I Used This Legendary Troll Question to IQ-Test 13 LLMs</title>
      <link>https://blog.margrop.net/en/post/llm-ruozhiba-chess-iq-test/</link>
      <pubDate>Fri, 14 Aug 2026 13:10:00 +0800</pubDate>
      <guid>https://blog.margrop.net/en/post/llm-ruozhiba-chess-iq-test/</guid>
      <description>&lt;blockquote&gt;&#xA;&lt;p&gt;&lt;strong&gt;Short version&lt;/strong&gt;&lt;/p&gt;&#xA;&lt;p&gt;I picked a classic trick question from Ruozhiba—the legendary Chinese forum famous for absurd brain-teasers—and asked it to 13 LLMs through my self-hosted NewAPI gateway: &lt;em&gt;&amp;ldquo;While playing chess, is it immoral to peek at your opponent&amp;rsquo;s board?&amp;rdquo;&lt;/em&gt; The results were dramatic: &lt;strong&gt;10 models spotted the trap&lt;/strong&gt; (in chess, both players share ONE public board—there is no &amp;ldquo;opponent&amp;rsquo;s board&amp;rdquo; to peek at), &lt;strong&gt;1 model failed at first then talked itself out of the hole&lt;/strong&gt;, &lt;strong&gt;2 models fell straight in and started moralizing&lt;/strong&gt;, and &lt;strong&gt;1 model simply told me to &amp;ldquo;refresh the page and try again.&amp;rdquo;&lt;/strong&gt; This is an unofficial, just-for-fun IQ report. Every answer is a real API response, archived with screenshots.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
