<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Test-Time Search on Programmer.ie</title>
    <link>http://programmer.ie/tags/test-time-search/</link>
    <description>Recent content in Test-Time Search on Programmer.ie</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 26 Aug 2026 10:00:00 +0100</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/test-time-search/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Building the Complete Agent</title>
      <link>http://programmer.ie/books/agents-from-first-principles/11-chapter/</link>
      <pubDate>Wed, 26 Aug 2026 10:00:00 +0100</pubDate>
      <guid>http://programmer.ie/books/agents-from-first-principles/11-chapter/</guid>
      <description>&lt;p&gt;Every mechanism in this book was argued against a problem chosen to isolate it.&lt;/p&gt;&#xA;&lt;p&gt;That isolation was deliberate, and it was also a form of protection. The memory chapter picked a task where recall was the bottleneck, held everything else still, and measured the one thing it came to measure. The result is a clean explanation and a weak claim. Nothing in it establishes that the same retrieval policy behaves when a search controller is expanding forty nodes, or when a verifier insists that every piece of evidence carry a state identity the search controller has never heard of.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
