<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Tool Use on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/tags/tool-use/</link>
    <description>Recent content in Tool Use on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 08 Aug 2026 15:40:00 +0100</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/tool-use/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Agents From First Principles 00: What Is an Agent, Really?</title>
      <link>http://programmer.ie/post/agents-from-first-principles-00/</link>
      <pubDate>Sat, 08 Aug 2026 15:40:00 +0100</pubDate>
      <guid>http://programmer.ie/post/agents-from-first-principles-00/</guid>
      <description>&lt;h1 id=&#34;what-is-an-agent-really&#34;&gt;What Is an Agent, Really?&lt;/h1&gt;&#xA;&lt;p&gt;This is the first post in &lt;strong&gt;Agents From First Principles&lt;/strong&gt;.&lt;/p&gt;&#xA;&lt;p&gt;It follows two earlier series.&lt;/p&gt;&#xA;&lt;p&gt;In &lt;strong&gt;PyTorch: Zero to Hero&lt;/strong&gt;, we worked upward from tensors, autograd and neural-network building blocks until we could build a small language model ourselves.&lt;/p&gt;&#xA;&lt;p&gt;In &lt;strong&gt;Models From First Principles&lt;/strong&gt;, we moved one level higher. We looked at how learned components can be composed into scorers, value models, policy heads, recurrent models, hierarchical models and compact recursive systems.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
