<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Cost on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/tags/cost/</link>
    <description>Recent content in Cost on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 14 Sep 2026 05:00:10 +0100</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/cost/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The Price of Intelligence</title>
      <link>http://programmer.ie/books/applied-ai/06-chapter/</link>
      <pubDate>Mon, 14 Sep 2026 05:00:06 +0100</pubDate>
      <guid>http://programmer.ie/books/applied-ai/06-chapter/</guid>
      <description>&lt;p&gt;&lt;em&gt;Part 1 — Where You Stand&lt;/em&gt;&lt;/p&gt;&#xA;&lt;h2 id=&#34;the-invoice-nobody-runs-at-prototype-time&#34;&gt;The invoice nobody runs at prototype time&lt;/h2&gt;&#xA;&lt;p&gt;The paragraph review from Chapter 1 costs about 1,200 tokens in and 400 out. At prototype scale that is a rounding error, and it is why nobody computes the next four numbers.&lt;/p&gt;&#xA;&lt;p&gt;A manuscript has 3,000 paragraphs. That is one full pass.&lt;/p&gt;&#xA;&lt;p&gt;The review is not run once. Every edit invalidates the review of the paragraph it touched, and a careful author edits most paragraphs four or five times.&lt;/p&gt;</description>
    </item>
    <item>
      <title>A Revolver, Not a Foundation</title>
      <link>http://programmer.ie/books/applied-ai/10-chapter/</link>
      <pubDate>Mon, 14 Sep 2026 05:00:10 +0100</pubDate>
      <guid>http://programmer.ie/books/applied-ai/10-chapter/</guid>
      <description>&lt;p&gt;&lt;em&gt;Part 2 — Get the Model Out of the Chat Box&lt;/em&gt;&lt;/p&gt;&#xA;&lt;h2 id=&#34;the-book-you-could-write-better-next-year&#34;&gt;The book you could write better next year&lt;/h2&gt;&#xA;&lt;p&gt;Write a book with AI this year and you will be able to write the same book better next year. And better again the year after. The same is true of the code, the research synthesis, the review process, the classifier — anything where a model does part of the work.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
