<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLM on Kianoosh's Blog</title><link>https://kianoosh.dev/tags/llm/</link><description>Recent content in LLM on Kianoosh's Blog</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Thu, 25 Dec 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://kianoosh.dev/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>The Maintenance Cliff: LLMs and the Learning Loop</title><link>https://kianoosh.dev/posts/2025-12-25-the-maintenance-cliff-llms-and-the-learning-loop/</link><pubDate>Thu, 25 Dec 2025 00:00:00 +0000</pubDate><guid>https://kianoosh.dev/posts/2025-12-25-the-maintenance-cliff-llms-and-the-learning-loop/</guid><description>&lt;h2 id="the-assembly-line-fallacy">The Assembly Line Fallacy&lt;/h2>
&lt;p>In our industry, there is a persistent temptation to treat software engineering like an assembly line. We constantly aim to abstract work into higher-level languages, reusable components, and &amp;ldquo;black box&amp;rdquo; services to increase velocity.&lt;/p>
&lt;p>In a recent article on MartinFowler.com, &lt;strong>Unmesh Joshi&lt;/strong> critiques this tendency. He argues that this efficiency-obsessed approach clashes with the most fundamental property of our work: &lt;strong>learning&lt;/strong>.&lt;/p>
&lt;p>When we rely entirely on readymade solutions without understanding the &amp;ldquo;why&amp;rdquo; and &amp;ldquo;how&amp;rdquo; underneath, we treat code as a static asset rather than a dynamic expression of knowledge.&lt;/p></description></item></channel></rss>