<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Least-Privilege AI on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/tags/least-privilege-ai/</link>
    <description>Recent content in Least-Privilege AI on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 02 Jun 2026 18:54:26 +0100</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/least-privilege-ai/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Warranted Search: When AI Must Prove Before It Looks</title>
      <link>http://programmer.ie/post/grep/</link>
      <pubDate>Tue, 02 Jun 2026 18:54:26 +0100</pubDate>
      <guid>http://programmer.ie/post/grep/</guid>
      <description>&lt;h2 id=&#34;tldr&#34;&gt;TL;DR&lt;/h2&gt;&#xA;&lt;p&gt;Modern AI systems often retrieve nearby text and generate confident answers, but that is not the same as proof. A citation can be real, the answer can be correct, and the evidence can still fail to support the claim.&lt;/p&gt;&#xA;&lt;p&gt;This post argues for &lt;strong&gt;warranted search&lt;/strong&gt;: a scoped, claim-driven form of intelligent grep. Instead of asking an AI to rummage through a corpus, we give it a specific claim, a bounded search warrant, and a limited set of safe operations.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
