<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Examples on Programmer.ie</title>
    <link>http://programmer.ie/tags/examples/</link>
    <description>Recent content in Examples on Programmer.ie</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 28 Aug 2026 10:30:00 +0100</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/examples/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>DSPy From First Principles 07: Examples Are Data, Not Decoration</title>
      <link>http://programmer.ie/books/dspy-from-first-principles/07-chapter/</link>
      <pubDate>Fri, 28 Aug 2026 10:30:00 +0100</pubDate>
      <guid>http://programmer.ie/books/dspy-from-first-principles/07-chapter/</guid>
      <description>&lt;h1 id=&#34;examples-are-data-not-decoration&#34;&gt;Examples Are Data, Not Decoration&lt;/h1&gt;&#xA;&lt;p&gt;Chapter 6 gave the program a model boundary. We can now say what the program is, which LM dependency ran it, and whether fallback output contaminated the record.&lt;/p&gt;&#xA;&lt;p&gt;That still leaves the unresolved problem:&lt;/p&gt;&#xA;&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; style=&#34;color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;&#34;&gt;&lt;code class=&#34;language-text&#34; data-lang=&#34;text&#34;&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;program&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;   ↓&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;no disciplined evidence&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;   ↓&#xA;&lt;/span&gt;&lt;/span&gt;&lt;span style=&#34;display:flex;&#34;&gt;&lt;span&gt;&amp;#34;seems better&amp;#34;&#xA;&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;The next six chapters build one deliberately small teaching experiment. We will keep the editorial sentence-improvement program, create a dataset, measure a baseline, design a metric, compile candidate programs, and compare them against a held-out case.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
