<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>ai on blog.jessefitzgerald</title><link>https://blog.jessefitzgerald.com/blog/ai/</link><description>Recent content in ai on blog.jessefitzgerald</description><generator>Hugo</generator><language>en-AU</language><lastBuildDate>Wed, 09 Sep 2026 06:11:00 +0000</lastBuildDate><atom:link href="https://blog.jessefitzgerald.com/blog/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>when one of the workers decided it was the boss</title><link>https://blog.jessefitzgerald.com/when-one-of-the-workers-decided-it-was-the-boss/</link><pubDate>Wed, 09 Sep 2026 06:11:00 +0000</pubDate><guid>https://blog.jessefitzgerald.com/when-one-of-the-workers-decided-it-was-the-boss/</guid><description>&lt;p>I&amp;rsquo;ve been working on a project to standardise the naming and tagging of my music collection. It&amp;rsquo;s a big job, so I&amp;rsquo;m processing albums in large batches using Beets, the Discogs API and Claude Code, with the aim of automating as much of the workflow as I can.&lt;/p>
&lt;p>It&amp;rsquo;s more involved than it sounds. Different formats need different treatment (DFF files have to be converted to DSF before anything else can happen), artwork has to be sourced according to a specific set of rules, metadata has to be matched against Discogs, and then everything has to be renamed and tagged consistently.&lt;/p></description></item></channel></rss>