<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>avidpolymath</title><link>https://avidpolymath.com/</link><description>Recent content on avidpolymath</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 14 Apr 2026 12:00:00 -0600</lastBuildDate><atom:link href="https://avidpolymath.com/index.xml" rel="self" type="application/rss+xml"/><item><title>TidyTodos</title><link>https://avidpolymath.com/projects/tidytodos/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://avidpolymath.com/projects/tidytodos/</guid><description/></item><item><title>Why I Prefer Opinionated Frameworks When Using LLMs</title><link>https://avidpolymath.com/posts/convention-over-configuration/</link><pubDate>Tue, 14 Apr 2026 12:00:00 -0600</pubDate><guid>https://avidpolymath.com/posts/convention-over-configuration/</guid><description>&lt;p&gt;The more I use LLMs to write code in today&amp;rsquo;s brave new world, the more I appreciate old opinionated frameworks like Ruby on Rails. While I can&amp;rsquo;t say for certain if LLMs write better code using these frameworks, the output is certainly far easier to reason about in your head.&lt;/p&gt;
&lt;p&gt;Since LLMs reduce the cost of writing code to near zero, there&amp;rsquo;s a tendency to move much faster and write more lines of code, which can lead to a drop in understanding what&amp;rsquo;s happening in a code base. And that&amp;rsquo;s dangerous over time.&lt;/p&gt;</description></item></channel></rss>