<?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>Ollaya on Bits-Entangled</title><link>https://stondo.github.io/tags/ollaya/</link><description>Recent content in Ollaya on Bits-Entangled</description><generator>Hugo -- 0.162.1</generator><language>en-us</language><lastBuildDate>Fri, 02 Oct 2026 09:00:00 +0000</lastBuildDate><atom:link href="https://stondo.github.io/tags/ollaya/index.xml" rel="self" type="application/rss+xml"/><item><title>One Coding Agent, Three GPUs, Two Cloud Keys: Local-First Routing and the Judge That Was Quietly Burning My 5090</title><link>https://stondo.github.io/posts/omp-local-first-routing-homelab-fleet/</link><pubDate>Fri, 02 Oct 2026 09:00:00 +0000</pubDate><guid>https://stondo.github.io/posts/omp-local-first-routing-homelab-fleet/</guid><description>I audited the model routing of my coding agent over the three-box fleet and found one dead fallback, one silent GPU tax, and one model name that does not exist. The fix routing: local models carry the token volume, cloud keys carry the decisions, and a 0.9-second local decision model now does every internal judgment.</description></item></channel></rss>