<?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>Chat-Template on GPUburnout | Jun Park</title><link>https://gpuburnout.com/tags/chat-template/</link><description>Recent content in Chat-Template 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>Wed, 27 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://gpuburnout.com/tags/chat-template/index.xml" rel="self" type="application/rss+xml"/><item><title>It Took Me Two Weeks to Read My Own Code</title><link>https://gpuburnout.com/posts/s5-ch4-two-weeks-read-my-own-code/</link><pubDate>Wed, 27 May 2026 00:00:00 +0000</pubDate><guid>https://gpuburnout.com/posts/s5-ch4-two-weeks-read-my-own-code/</guid><description>I shipped a 3B chat model in April. It scored 8 points worse than my 2B on the most important benchmark. The bug was twelve lines of Python I had never read.</description></item></channel></rss>