<?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>Visual-Qa on Pavel Nasovich's Blog</title><link>https://forcewake.me/tags/visual-qa/</link><description>Recent content in Visual-Qa on Pavel Nasovich's Blog</description><generator>Hugo -- 0.157.0</generator><language>en-us</language><copyright>Copyright 2026</copyright><lastBuildDate>Fri, 17 Apr 2026 02:25:22 +0200</lastBuildDate><atom:link href="https://forcewake.me/tags/visual-qa/index.xml" rel="self" type="application/rss+xml"/><item><title>I Ran pi on Qwen3.6 35B A3B via llama-server. It Built the Deck and QA'd Itself</title><link>https://forcewake.me/pi-qwen36-llamacpp-self-healing-local-agent/</link><pubDate>Thu, 16 Apr 2026 18:58:26 +0000</pubDate><guid>https://forcewake.me/pi-qwen36-llamacpp-self-healing-local-agent/</guid><description>A first-person technical deep dive into serving Unsloth&amp;#39;s Qwen3.6 35B A3B GGUF through llama-server with pi, then using it to research, generate a slide deck, run visual QA, and repair its own output locally.</description></item></channel></rss>