<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>Expertise on Programmer.ie: Modern AI programming</title>
		<link>http://programmer.ie/tags/expertise/</link>
		<description>Recent content in Expertise on Programmer.ie: Modern AI programming</description>
		<generator>Hugo</generator>
		<language>en-US</language>
		
		
		
		
			<lastBuildDate>Fri, 20 Nov 2026 10:00:00 +0000</lastBuildDate>
		
			<atom:link href="http://programmer.ie/tags/expertise/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>There Is No Universal Best Interface</title>
				<link>http://programmer.ie/books/language/23-chapter/</link>
				<pubDate>Thu, 01 Oct 2026 09:00:00 +0100</pubDate>
				<guid>http://programmer.ie/books/language/23-chapter/</guid>
				<description>&lt;p&gt;The previous chapter ended with a temptation. Iris&amp;rsquo;s behaviour leaves traces. In the constructed session, she opens tables more often than prose, expands mathematical detail and leaves some diagrams unopened. A system with memory could turn these events into a convenient description: this person is a certain kind of reader. It could then serve that supposed type everywhere, without asking again. But the trace does not record what alternatives were available, why she opened each view, or whether she performed better afterwards. The classification would already be claiming more than the observation showed.&lt;/p&gt;</description>
			</item>
			<item>
				<title>I Don&#39;t Write Code Anymore</title>
				<link>http://programmer.ie/post/code/</link>
				<pubDate>Fri, 20 Nov 2026 10:00:00 +0000</pubDate>
				<guid>http://programmer.ie/post/code/</guid>
				<description>&lt;p&gt;Two years ago, I lived in code. I wrote it, read it, debugged it and spent much of my working day trying to understand why something wasn&amp;rsquo;t doing what I expected.&lt;/p&gt;&#xA;&lt;p&gt;I don&amp;rsquo;t work like that anymore.&lt;/p&gt;&#xA;&lt;p&gt;Today, I spend perhaps one to five per cent of my time looking at code, and on many days I don&amp;rsquo;t look at any. I don&amp;rsquo;t read test cases or use a debugger. If something fails, I describe the failure to an AI and have it investigate. That isn&amp;rsquo;t a temporary experiment or a plan for how I might work in the future. It&amp;rsquo;s how I work now.&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
