<?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>Code-Review on Local First AI</title><link>https://localfirstai.eu/tags/code-review/</link><description>Recent content in Code-Review on Local First AI</description><image><title>Local First AI</title><url>https://localfirstai.eu/images/og-default.png</url><link>https://localfirstai.eu/images/og-default.png</link></image><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 19 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://localfirstai.eu/tags/code-review/index.xml" rel="self" type="application/rss+xml"/><item><title>Tests One AI Agent Wrote for Another Were Wrong in 7 of 13 Runs</title><link>https://localfirstai.eu/posts/2026-11-19-tests-one-agent-wrote-for-another/</link><pubDate>Thu, 19 Nov 2026 00:00:00 +0000</pubDate><guid>https://localfirstai.eu/posts/2026-11-19-tests-one-agent-wrote-for-another/</guid><description>The usual advice for coding agents is to write the test first and let the agent work until it passes. A record of thirteen runs on real work, with a table of the defects: the test was wrong in about half of them, one fix passed its tests by stepping aside from the question, and a reviewer who was not given the worker&amp;#39;s report found most of what was found.</description></item></channel></rss>