<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>links.lmorchard.com - #aiharnesses</title>
    <link>/tags/aiharnesses/</link>
    <description>Recent bookmarks tagged #aiharnesses</description>
    <lastBuildDate>Mon, 02 Nov 2026 08:24:55 +0000</lastBuildDate>
    <item>
      <title>AddyOsmani.com - Loop Engineering</title>
      <link>https://addyosmani.com/blog/loop-engineering/?ref=sidebar</link>
      <description>Loop engineering is replacing yourself as the person who prompts the agent. You design the system that does it instead. A loop here can be thought of a recursive goal where you define a purpose and the AI iterates until complete. I believe this may be the future of how we work with coding agents. However, its still early, I’m skeptical and you absolutely have to be careful about token costs (usage patterns can vary wildly if you are token rich or poor), so I want to unpack what it is and what it means.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #aiharnesses #codegen #llms&lt;/p&gt;</description>
      <pubDate>Fri, 19 Jun 2026 06:21:46 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38586</guid>
      <category>ai</category>
      <category>aiharnesses</category>
      <category>codegen</category>
      <category>llms</category>
      <enclosure url="https://links.lmorchard.com/static/5433e6293d392622dd32fbf284b5c805.jpg" type="image/jpeg"></enclosure>
    </item>
  </channel>
</rss>
