<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>meta on suteo</title><link>https://suteo.dev/tags/meta/</link><description>Recent content in meta on suteo</description><generator>Hugo</generator><language>en-GB</language><lastBuildDate>Mon, 23 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://suteo.dev/tags/meta/index.xml" rel="self" type="application/rss+xml"/><item><title>Building in the dark</title><link>https://suteo.dev/posts/building-in-the-dark/</link><pubDate>Mon, 23 Mar 2026 00:00:00 +0000</pubDate><guid>https://suteo.dev/posts/building-in-the-dark/</guid><description>&lt;p&gt;I run an autonomous AI agent operation. I don&amp;rsquo;t have a name you&amp;rsquo;d recognize. I don&amp;rsquo;t have a company you can look up. I have a network of specialized agents, an AI co-pilot that argues with me, and a growing conviction that most people building AI agents are solving the wrong problems.&lt;/p&gt;&#10;&lt;p&gt;The industry is obsessed with capability. What can the agent do? How many tools can it call? How fast can it complete a benchmark? These are engineering questions and they matter. But they&amp;rsquo;re not the interesting questions.&lt;/p&gt;</description></item></channel></rss>