<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Pre-Declared Criteria on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/tags/pre-declared-criteria/</link>
    <description>Recent content in Pre-Declared Criteria on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 14 Aug 2026 10:30:00 +0100</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/pre-declared-criteria/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>05: So We Built the Wrong Thing on Purpose</title>
      <link>http://programmer.ie/books/digital-life/05-so-we-built-the-wrong-thing-on-purpose/</link>
      <pubDate>Fri, 14 Aug 2026 10:30:00 +0100</pubDate>
      <guid>http://programmer.ie/books/digital-life/05-so-we-built-the-wrong-thing-on-purpose/</guid>
      <description>&lt;p&gt;The previous chapter ended with a specification.&lt;/p&gt;&#xA;&lt;p&gt;Known rules, controlled interventions, one mechanism varied at a time, a history we can follow. That is the laboratory we will eventually need, and building it is most of the work still ahead.&lt;/p&gt;&#xA;&lt;p&gt;Before building it, there is a cheaper question.&lt;/p&gt;&#xA;&lt;p&gt;Are our tests any good?&lt;/p&gt;&#xA;&lt;p&gt;That is not an idle worry. The last chapter produced the first positive result in this book. A bounded one, but a real one: structural recurrence intersected with causal ancestry, and a causal claim survived a test we had not designed to make it pass.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
