<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Software Engineering on MagneticFlux LLC</title>
    <link>https://mw.magneticflux.net/tags/software-engineering/</link>
    <description>Recent content in Software Engineering on MagneticFlux LLC</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <copyright>This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.</copyright>
    <lastBuildDate>Mon, 30 Mar 2026 12:00:00 +0000</lastBuildDate>
    <atom:link href="https://mw.magneticflux.net/tags/software-engineering/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Dijkstra, Coding Agents, and the Limits of Natural-Language Programming</title>
      <link>https://mw.magneticflux.net/posts/programming/dijkstra-coding-agents-and-natural-language-programming/</link>
      <pubDate>Mon, 30 Mar 2026 12:00:00 +0000</pubDate>
      <guid>https://mw.magneticflux.net/posts/programming/dijkstra-coding-agents-and-natural-language-programming/</guid>
      <description>AI coding assistants have made natural language a far more powerful front-end for software development, but that does not mean English has become a programming language in Dijkstra&amp;rsquo;s stronger sense. The important distinction is not between prompts and code alone, but between informal steering, empirical development loops, and programs understood as formal artifacts whose correctness can be reasoned about.</description>
    </item>
  </channel>
</rss>
