<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Harness-Engineering on Notes from the Rabbit Hole</title><link>https://magnus919.com/tags/harness-engineering/</link><description>Recent content in Harness-Engineering on Notes from the Rabbit Hole</description><generator>Hugo</generator><language>en</language><copyright>© [Magnus Hedemark](https://github.com/magnus919)</copyright><lastBuildDate>Wed, 24 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://magnus919.com/tags/harness-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>Stop Picking Models. Start Building Harnesses.</title><link>https://magnus919.com/2026/06/stop-picking-models.-start-building-harnesses./</link><pubDate>Wed, 24 Jun 2026 00:00:00 +0000</pubDate><guid>https://magnus919.com/2026/06/stop-picking-models.-start-building-harnesses./</guid><description>&lt;p>Most companies are playing a game they don&amp;rsquo;t understand the rules to. They&amp;rsquo;re standing in a room full of competitors, all of them staring at the same two doors. One door says OpenAI. The other says Anthropic. They believe the strategic decision is which door to walk through. They believe this so deeply that they&amp;rsquo;re paying enormous premiums for inference that&amp;rsquo;s past the point of diminishing returns, and getting nothing their competitors aren&amp;rsquo;t also getting.&lt;/p></description></item></channel></rss>