<?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>Claude on Swaranga Sarma</title><link>https://swaranga.dev/tags/claude/</link><description>Recent content in Claude on Swaranga Sarma</description><image><title>Swaranga Sarma</title><url>https://swaranga.dev/images/profile.jpg</url><link>https://swaranga.dev/images/profile.jpg</link></image><generator>Hugo</generator><language>en</language><lastBuildDate>Wed, 15 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://swaranga.dev/tags/claude/index.xml" rel="self" type="application/rss+xml"/><item><title>My experience with Claude and Codex on a system architecture bug</title><link>https://swaranga.dev/posts/claude-vs-codex-on-a-system-architecture-bug/</link><pubDate>Wed, 15 Apr 2026 00:00:00 +0000</pubDate><guid>https://swaranga.dev/posts/claude-vs-codex-on-a-system-architecture-bug/</guid><description>I gave two state-of-the-art AI models the same architecture bug. I was quite surprised with the difference in results.</description></item></channel></rss>