<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Learning on Fabian G. Williams</title><link>https://www.fabswill.com/categories/learning/</link><description>Recent content in Learning on Fabian G. Williams</description><image><title>Fabian G. Williams</title><url>https://www.fabswill.com/img/main/logo.jpg</url><link>https://www.fabswill.com/img/main/logo.jpg</link></image><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 08 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.fabswill.com/categories/learning/index.xml" rel="self" type="application/rss+xml"/><item><title>Weekday Judge, Weekend Judge, and Now a Microscope</title><link>https://www.fabswill.com/blog/weekday-judge-weekend-judge/</link><pubDate>Sun, 08 Nov 2026 00:00:00 +0000</pubDate><guid>https://www.fabswill.com/blog/weekday-judge-weekend-judge/</guid><description>For a few weekends I&amp;#39;ve been grading my own AI and the Ontology it answers from: a local model judges it every night, I judge it by hand every weekend. This weekend 2 conference talks confirmed what my grading had already been telling me, and I turned them into code the same day. I also opened up my traces, so now I can follow every question from my words to the model&amp;#39;s answer, step by step. Here&amp;#39;s what I built, what broke, and what I&amp;#39;m testing next week.</description></item></channel></rss>