<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>links.lmorchard.com - #qwen</title>
    <link>/tags/qwen/</link>
    <description>Recent bookmarks tagged #qwen</description>
    <lastBuildDate>Sun, 22 Nov 2026 12:25:35 +0000</lastBuildDate>
    <item>
      <title>Qwen 3.8 27B on my laptop can interpret model weights, too</title>
      <link>https://simonwillison.net/2026/Nov/3/qwen-can-interpret-model-weights/</link>
      <description>It’s a cool paper, but some of the wider commentary I’ve seen around it does not feel justified. I’m not ready to declare that the age of source code is over and our future involves incomprehensible machines editing their own model weights in incomprehensible ways.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #llms #ml #qwen&lt;/p&gt;</description>
      <pubDate>Sat, 21 Nov 2026 19:21:56 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38860</guid>
      <category>ai</category>
      <category>llms</category>
      <category>ml</category>
      <category>qwen</category>
    </item>
  </channel>
</rss>
