<?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 Matt W Marshall</title><link>https://mattwmarshall.com/categories/ai/</link><description>Recent content in AI on Matt W Marshall</description><generator>Hugo</generator><language>en</language><copyright>© Matt Marshall</copyright><lastBuildDate>Wed, 15 Jul 2026 14:20:50 -0700</lastBuildDate><atom:link href="https://mattwmarshall.com/categories/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>A Personalized LLM Benchmark</title><link>https://mattwmarshall.com/posts/2026-07-15-personalized-llm-benchmark/</link><pubDate>Wed, 15 Jul 2026 14:20:50 -0700</pubDate><guid>https://mattwmarshall.com/posts/2026-07-15-personalized-llm-benchmark/</guid><description>A custom 26-test benchmark across seven categories, run on my home AI box to see which local LLM actually wins.</description></item></channel></rss>