<?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>Fuzzy-Matcher on GPUburnout | Jun Park</title><link>https://gpuburnout.com/tags/fuzzy-matcher/</link><description>Recent content in Fuzzy-Matcher on GPUburnout | Jun Park</description><image><title>GPUburnout | Jun Park</title><url>https://gpuburnout.com/images/og-default.png</url><link>https://gpuburnout.com/images/og-default.png</link></image><generator>Hugo -- 0.155.2</generator><language>en-us</language><lastBuildDate>Mon, 25 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://gpuburnout.com/tags/fuzzy-matcher/index.xml" rel="self" type="application/rss+xml"/><item><title>Bigger Is Not Safer</title><link>https://gpuburnout.com/posts/s6-ch3-bigger-is-not-safer/</link><pubDate>Mon, 25 May 2026 00:00:00 +0000</pubDate><guid>https://gpuburnout.com/posts/s6-ch3-bigger-is-not-safer/</guid><description>Every time the matcher stumbled, I wanted to let the model fix it. So I tested that idea. The model talked me out of it.</description></item><item><title>Where the Deterministic Line Goes</title><link>https://gpuburnout.com/posts/s6-ch2-where-the-deterministic-line-goes/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://gpuburnout.com/posts/s6-ch2-where-the-deterministic-line-goes/</guid><description>The obvious fix is to let the model guess and check its work against the database. That is exactly the fix that does not work.</description></item></channel></rss>