<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Frames on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/tags/frames/</link>
    <description>Recent content in Frames on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 14 Sep 2026 05:00:13 +0100</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/frames/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>When the Frame Is Wrong</title>
      <link>http://programmer.ie/books/memory/13-chapter/</link>
      <pubDate>Mon, 14 Sep 2026 05:00:13 +0100</pubDate>
      <guid>http://programmer.ie/books/memory/13-chapter/</guid>
      <description>&lt;p&gt;Chapter 12 ended with leverage: wrong memory averages 0.042 with two harmful tasks, so a layer that decides what the model may see can cause the harmful action rather than merely failing to prevent it. The next question is when the system should trust its own framing that strongly. Chapter 10 specified the missing piece without building it — a frame that carries how it was established, with conditioning that weakens as the evidence degrades toward query-only retrieval. This chapter builds that piece and measures whether it earns its place.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
