<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Engineering on ./Code</title><link>https://blog.ouankou.com/tags/engineering/</link><description>Recent content in Engineering on ./Code</description><generator>Hugo</generator><language>en-US</language><copyright>© Anjia Wang</copyright><lastBuildDate>Mon, 25 May 2026 13:40:11 -0700</lastBuildDate><atom:link href="https://blog.ouankou.com/tags/engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>What A Twelve-Day Codex Session Revealed About Persistent Engineering Agents</title><link>https://blog.ouankou.com/2026/05/28/what-a-twelve-day-codex-session-revealed-about-persistent-engineering-agents/</link><pubDate>Thu, 28 May 2026 00:00:00 +0000</pubDate><guid>https://blog.ouankou.com/2026/05/28/what-a-twelve-day-codex-session-revealed-about-persistent-engineering-agents/</guid><description>&lt;p&gt;The REX frozen-failure cleanup was a compiler project, but it was also an agent project.&lt;/p&gt;
&lt;p&gt;For twelve days, Codex worked through a large historical CTest failure set in a real codebase. The task was not a toy benchmark. It involved a Clang frontend, a source-to-source AST, an unparser, token and source-position preservation, OpenMP and Fortran guardrails, midend analyses, generated files, reference outputs, review comments, hooks, and full-suite CTest runs.&lt;/p&gt;
&lt;p&gt;That is the kind of task where many agent demos stop being useful.&lt;/p&gt;</description></item></channel></rss>