<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Embeddings on Antonio Cortés (DrZippie)</title><link>https://antoniocortes.com/en/tags/embeddings/</link><description>Recent content in Embeddings on Antonio Cortés (DrZippie)</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 10 Aug 2026 23:32:39 +0200</lastBuildDate><atom:link href="https://antoniocortes.com/en/tags/embeddings/index.xml" rel="self" type="application/rss+xml"/><item><title>Classifying 29,559 local news items with AI on a laptop</title><link>https://antoniocortes.com/en/clasificar-29000-noticias-ia-local/</link><pubDate>Mon, 10 Aug 2026 00:00:00 +0000</pubDate><guid>https://antoniocortes.com/en/clasificar-29000-noticias-ia-local/</guid><description>&lt;p&gt;&lt;a href="https://pontecesures.net/"&gt;&lt;code&gt;pontecesures.net&lt;/code&gt;&lt;/a&gt; is a personal project I&amp;rsquo;ve been running for years: the news portal of &lt;a href="https://en.wikipedia.org/wiki/Pontecesures"&gt;Pontecesures&lt;/a&gt;, my home town, a Galician municipality of about 3,000 people. The idea has always been a simple one — keeping the information about what happens there alive. Twenty-one years of archive, from 2005 to 2026, &lt;strong&gt;29,559 entries&lt;/strong&gt;.&lt;/p&gt;
&lt;p&gt;The problem is that most of them are uncategorised or categorised inconsistently. When you&amp;rsquo;ve been publishing for two decades, taxonomies decay on their own: I ended up with 56 categories that no longer meant anything. An archive like that stops being browsable, and at that point much of its value is lost. It&amp;rsquo;s exactly the kind of task you keep putting off, and one I had wanted to tackle for a long time.&lt;/p&gt;</description></item></channel></rss>