<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Systems on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/tags/systems/</link>
    <description>Recent content in Systems on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 14 Sep 2026 05:00:17 +0100</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/systems/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The Remembering System</title>
      <link>http://programmer.ie/books/memory/17-chapter/</link>
      <pubDate>Mon, 14 Sep 2026 05:00:17 +0100</pubDate>
      <guid>http://programmer.ie/books/memory/17-chapter/</guid>
      <description>&lt;p&gt;The book began with a deliberately strict definition:&lt;/p&gt;&#xA;&lt;blockquote&gt;&#xA;&lt;p&gt;&lt;strong&gt;Memory is when retained past experience changes what the system does now.&lt;/strong&gt;&lt;/p&gt;&lt;/blockquote&gt;&#xA;&lt;p&gt;Everything else — vector stores, graphs, temporal state, context selection, consolidation, procedures — is mechanism.&lt;/p&gt;&#xA;&lt;p&gt;That distinction changes what a final chapter should do.&lt;/p&gt;&#xA;&lt;p&gt;The original plan saved the behavioural test for the twentieth chapter and imagined a full stack in front of it: events, claims, provenance, belief, open loops, policy, context assembly, consolidation, compression, forgetting, outcome adaptation, procedures, then behaviour. The experiments did not follow that plan. Selection moved earlier. Context assembly was measured before long-term compression. Derived state produced both benefits and hazards. Simple mechanisms repeatedly matched or beat ambitious ones. Chapter 12 was moved forward specifically to test the behavioural definition before the book accumulated more machinery.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
