<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Llm on Rusty Bower</title><link>https://www.rustybower.com/categories/llm/</link><description>Recent content in Llm on Rusty Bower</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© Rusty Bower</copyright><lastBuildDate>Tue, 28 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.rustybower.com/categories/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Teaching Security Cameras to Describe What They See</title><link>https://www.rustybower.com/posts/frigate-coral-tpu-vision-llm-camera-alerts/</link><pubDate>Tue, 28 Jul 2026 00:00:00 +0000</pubDate><guid>https://www.rustybower.com/posts/frigate-coral-tpu-vision-llm-camera-alerts/</guid><description>&lt;p&gt;A notification that says &amp;ldquo;person detected on doorbell&amp;rdquo; is useful. A notification that says &amp;ldquo;a delivery driver in a brown UPS uniform placed a medium-sized box on the porch and is walking back to the truck&amp;rdquo; is significantly more useful — especially when you&amp;rsquo;re in a meeting and trying to decide whether to get up.&lt;/p&gt;</description></item><item><title>Mac Studio as a Kubernetes Compute Satellite</title><link>https://www.rustybower.com/posts/mac-studio-kubernetes-compute-satellite/</link><pubDate>Tue, 21 Jul 2026 00:00:00 +0000</pubDate><guid>https://www.rustybower.com/posts/mac-studio-kubernetes-compute-satellite/</guid><description>&lt;p&gt;My K3s cluster runs on six Intel NUCs. They&amp;rsquo;re great for the 50+ containers that make up my homelab — Plex, Home Assistant, Frigate, Paperless, the usual suspects. But they&amp;rsquo;re terrible at machine learning. Four Skylake cores and 32 GB of RAM per node doesn&amp;rsquo;t get you far when Immich wants to classify 80,000 photos or Frigate wants a vision model to describe who&amp;rsquo;s at your door.&lt;/p&gt;</description></item><item><title>Fixing 10,000 Upside-Down Scanned Slides with a Local Vision LLM</title><link>https://www.rustybower.com/posts/fixing-upside-down-scanned-slides-vision-llm/</link><pubDate>Mon, 23 Feb 2026 00:00:00 +0000</pubDate><guid>https://www.rustybower.com/posts/fixing-upside-down-scanned-slides-vision-llm/</guid><description>&lt;p&gt;My grandfather had about 10,000 35mm slides. I rented a &lt;a href="https://www.slidesnap.com/" target="_blank" rel="noreferrer"&gt;SlideSnap X1&lt;/a&gt; and spent a weekend feeding them through — 33 boxes worth, organized into folders by box. The scanner itself was great, but when you&amp;rsquo;re pushing through thousands of slides in a weekend, some inevitably go in upside down or backwards. No metadata, no EXIF orientation flags — just thousands of JPEGs, some right-side up, some not, sitting on a NAS.&lt;/p&gt;</description></item></channel></rss>