<?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/tags/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>Mon, 02 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.fabswill.com/tags/learning/index.xml" rel="self" type="application/rss+xml"/><item><title>Learnings at Every Turn: A Frontier-Scale Router Comes Home</title><link>https://www.fabswill.com/blog/learnings-at-every-turn/</link><pubDate>Mon, 02 Nov 2026 00:00:00 +0000</pubDate><guid>https://www.fabswill.com/blog/learnings-at-every-turn/</guid><description>Abram Jackson put it plainly: &amp;#39;it&amp;#39;s not just a simple router. We use multiple models for a single request, based on which combination scores highest on our evals.&amp;#39; My home lab has been teaching me the same lesson from the other end. Learning flows both ways: what I prove at home on my own machines shapes what I take to work, and what I see at frontier scale at work shapes what I try at home. Here&amp;#39;s the latest turn, what my local AI does today, what I&amp;#39;m testing next weekend, and where I&amp;#39;m not there yet.</description></item></channel></rss>