<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Christian Weilbach</title><description>Essays and notes on learning systems, simulation and self-improvement.</description><link>https://christian.weilbach.name/</link><item><title>Who checks a system that improves itself?</title><link>https://christian.weilbach.name/writing/who-checks-a-system-that-improves-itself/</link><guid isPermaLink="true">https://christian.weilbach.name/writing/who-checks-a-system-that-improves-itself/</guid><description>A system that improves itself has to predict its own future, think through changes on forks and decide which ones to keep, while what it values changes with it. A programming model for this, built across a full stack from versioned memory to organisations of people and AI agents.</description><pubDate>Tue, 10 Nov 2026 00:00:00 GMT</pubDate></item></channel></rss>