<?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>Sqlite on Musings about technology</title><link>https://sirile.github.io/tags/sqlite/</link><description>Recent content in Sqlite on Musings about technology</description><generator>Hugo -- 0.157.0</generator><language>en-us</language><lastBuildDate>Tue, 07 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://sirile.github.io/tags/sqlite/index.xml" rel="self" type="application/rss+xml"/><item><title>What 2,000 beads taught me about multi-agent development</title><link>https://sirile.github.io/posts/2026-04-07-what-2000-beads-taught-me-about-multi-agent-development/</link><pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate><guid>https://sirile.github.io/posts/2026-04-07-what-2000-beads-taught-me-about-multi-agent-development/</guid><description>&lt;p&gt;Three weeks ago I wrote about &lt;a href="https://sirile.github.io/posts/2026-03-14-building-a-self-coordinating-ai-development-team/"&gt;building a self-coordinating AI development team&lt;/a&gt;. At that point the system had processed about 1,000 beads and was starting to feel like more than a prototype.&lt;/p&gt;
&lt;p&gt;Since then, the bead counter passed 3,400. The system has been running almost continuously on my laptop, building features, fixing its own bugs, and – most instructively – breaking in ways I didn&amp;rsquo;t anticipate.&lt;/p&gt;
&lt;p&gt;This is what I learned.&lt;/p&gt;</description></item></channel></rss>