<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Long Horizon on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/tags/long-horizon/</link>
    <description>Recent content in Long Horizon on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 23 Sep 2026 05:00:11 +0100</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/long-horizon/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Compression Is Loss</title>
      <link>http://programmer.ie/books/context/11-chapter/</link>
      <pubDate>Wed, 23 Sep 2026 05:00:11 +0100</pubDate>
      <guid>http://programmer.ie/books/context/11-chapter/</guid>
      <description>&lt;p&gt;An agent has accumulated a working past: an architecture decision at 500 tokens, an unresolved bug history at 4,000, three failed approaches at 8,000, tool observations at 20,000, the current implementation at 6,000. Chapter 10 does its honest work. Duplicates go, proven-superseded observations go, failed-input bulk goes with residues kept. Roughly 13,000 tokens leave. Twenty-five thousand remain, and every token of them matters in the sense this book has defined: some future computation may need it, and no rung of the evidence ladder licenses deletion. The bundle still does not fit the session ahead. Nothing left can disappear. Everything left cannot stay verbatim. That is where this chapter begins, at the exact point where deletion stops working.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
