<?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 Rohit Jha</title><link>https://www.rohitjha.dev/tags/software-engineering/</link><description>Recent content in Software Engineering on Rohit Jha</description><generator>Hugo</generator><language>en-US</language><copyright>© Rohit Jha. Articles licensed under CC BY-SA 4.0 unless noted.</copyright><lastBuildDate>Fri, 14 Aug 2026 14:26:46 +0530</lastBuildDate><atom:link href="https://www.rohitjha.dev/tags/software-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>What I Lose When AI Writes the Code</title><link>https://www.rohitjha.dev/blog/what-i-lose-when-ai-writes-the-code/</link><pubDate>Fri, 14 Aug 2026 00:00:00 +0000</pubDate><guid>https://www.rohitjha.dev/blog/what-i-lose-when-ai-writes-the-code/</guid><description>&lt;p&gt;I recently realized that I don&amp;rsquo;t enjoy using AI coding agents to implement substantial changes at work. They can shorten the path from an idea to working code. I am trying to understand why that productivity often makes the work less satisfying for me.&lt;/p&gt;
&lt;p&gt;My current explanation is that coding is part of how I think. The design continues to change as I implement it. A type that looked natural on paper becomes awkward at its call sites. An error path forces a decision about which layer owns recovery. A performance assumption sends me to a profile or generated assembly.&lt;/p&gt;</description></item></channel></rss>