<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>links.lmorchard.com - #godegen</title>
    <link>/tags/godegen/</link>
    <description>Recent bookmarks tagged #godegen</description>
    <lastBuildDate>Mon, 02 Nov 2026 08:24:56 +0000</lastBuildDate>
    <item>
      <title>Grieving the loss of details | purplesyringa&#39;s blog</title>
      <link>https://purplesyringa.moe/blog/grieving-the-loss-of-details/?ref=sidebar</link>
      <description>If anyone can point an LLM at slow code and it automatically finds a hot loop and uses a trick it found somewhere on the &#39;net to vectorize it, there is little point in hiring someone with a focus on that. If an LLM can analyze the code and explain pointer provenance to you and babysit you until you get it, there is little value in expertise.&#xA;&#xA;I cannot use LLMs this way. I get almost physically ill when I work on a project with more source code files or at least general architecture than I can keep in my head, so I don’t get anything out of expanded scope.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #godegen #llms&lt;/p&gt;</description>
      <pubDate>Wed, 14 Oct 2026 17:16:33 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38808</guid>
      <category>ai</category>
      <category>godegen</category>
      <category>llms</category>
      <enclosure url="https://links.lmorchard.com/static/da4c1570f55214db1ccaff2e2f215d61.png" type="image/png"></enclosure>
    </item>
  </channel>
</rss>
