<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI Models on No Semicolons</title><link>https://nosemicolons.com/tags/ai-models/</link><description>Recent content in AI Models on No Semicolons</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 25 Sep 2026 13:07:58 +0000</lastBuildDate><atom:link href="https://nosemicolons.com/tags/ai-models/index.xml" rel="self" type="application/rss+xml"/><item><title>The AI Code Generation Model Whisperer: How I Trained 5 Different Models to Write Code Like My Team</title><link>https://nosemicolons.com/posts/ai-code-generation-model-whisperer-training-multiple-models/</link><pubDate>Fri, 25 Sep 2026 13:07:58 +0000</pubDate><guid>https://nosemicolons.com/posts/ai-code-generation-model-whisperer-training-multiple-models/</guid><description>&lt;p>Ever wished your AI coding assistant actually understood your team&amp;rsquo;s conventions? You know the feeling — you ask ChatGPT to generate a React component and it comes back with class components when your team exclusively uses hooks, or it formats everything completely differently from your established patterns.&lt;/p>
&lt;p>Six months ago, I got tired of constantly correcting AI-generated code to match our team standards. So I decided to experiment: what if I could train different AI models to write code that actually looked like it came from our developers?&lt;/p></description></item></channel></rss>