<?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>Programming on Roadrunner</title><link>https://blog.roadrunner.motorcycles/programming/</link><description>Recent content in Programming on Roadrunner</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 22 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.roadrunner.motorcycles/programming/index.xml" rel="self" type="application/rss+xml"/><item><title>Stop the slop!</title><link>https://blog.roadrunner.motorcycles/programming/stop_the_slop/</link><pubDate>Wed, 22 Jul 2026 00:00:00 +0000</pubDate><guid>https://blog.roadrunner.motorcycles/programming/stop_the_slop/</guid><description>&lt;h1 id="ramblings-about-llms-from-a-guy-on-the-frontlines-banging-his-head-on-the-wall"&gt;Ramblings about LLMs from a guy on the frontlines banging his head on the wall&lt;/h1&gt;
&lt;p&gt;Over the past 6 months, I&amp;rsquo;ve had a dramatic change of heart regarding the use of generative AI for software development. Partially this has been caused by newer and better models such as Opus 4.8, but mostly because I made the leap from using a chat window within VSCode to using Claude Code on the terminal. I started by occasionally asking questions on the web interface of ChatGPT and being dissapointed when it hallucinated about the relatively niche library I was using, and from the introduction of GPT3 to the beginning of 2026, this was my experience of LLMs and it was sorely unimpressive.&lt;/p&gt;</description></item></channel></rss>