<?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 Paul's Particles</title><link>https://paulstapel.com/categories/ai/</link><description>Recent content in AI on Paul's Particles</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Sun, 24 May 2026 15:21:47 +0200</lastBuildDate><atom:link href="https://paulstapel.com/categories/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Some views on AI</title><link>https://paulstapel.com/context-engineering/</link><pubDate>Sun, 24 May 2026 15:21:47 +0200</pubDate><guid>https://paulstapel.com/context-engineering/</guid><description>AI, you may love it, you may hate it, but it&amp;rsquo;s here. Just like the rest of the world, I have been exposed to Large Language Models for a few years now, but only recently have I been able to see through the hype or criticism to actually form a coherent stand on what I think AI can and can&amp;rsquo;t do. Most importantly, despite initial criticism, I have come to appreciate that there is quite some craftsmanship in getting AI to actually do what you want it to, and that boils down most strongly to context engineering.</description></item></channel></rss>