<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Rust on René Zander | AI Automation Consultant</title><link>https://renezander.com/tags/rust/</link><description>Recent content in Rust on René Zander | AI Automation Consultant</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 07 Jul 2026 06:00:00 +0000</lastBuildDate><atom:link href="https://renezander.com/tags/rust/index.xml" rel="self" type="application/rss+xml"/><item><title>EdgeHome Harness: Why MiniCPM5-1B Never Touches Your Devices</title><link>https://renezander.com/blog/edgehome-harness-minicpm5-1b/</link><pubDate>Tue, 07 Jul 2026 06:00:00 +0000</pubDate><guid>https://renezander.com/blog/edgehome-harness-minicpm5-1b/</guid><description>&lt;p>Reliability in an AI agent is a harness property, not a model property.&lt;/p>
&lt;p>The cleanest proof arrived at the bottom of the model-size ladder: a 688 MB model controlling a smart home, showcased by the model&amp;rsquo;s own maker. The part worth studying is the 25 MB of Rust wrapped around it.&lt;/p>
&lt;p>EdgeHome Harness pairs MiniCPM5-1B, 688 MB on disk and about 1 GB at runtime, with a Rust harness between 25 and 64 MB, targeting devices with 2 GB of RAM. A community developer built it; OpenBMB put it on stage. The line everyone will quote is that a full agent stack fits on ultra-constrained edge hardware. The design decision that matters is different: the model is not allowed to do anything.&lt;/p></description></item></channel></rss>