<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>AI on Zdenek Jurman</title>
    <link>https://www.zdenek-jurman.cz/tags/ai/</link>
    <description>Recent content in AI on Zdenek Jurman</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Sat, 11 Jul 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://www.zdenek-jurman.cz/tags/ai/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Mesh LLM</title>
      <link>https://www.zdenek-jurman.cz/posts/mesh-llm/</link>
      <pubDate>Sat, 11 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://www.zdenek-jurman.cz/posts/mesh-llm/</guid>
      <description>&lt;p&gt;Mesh LLM pools GPUs and memory across machines and exposes the result as one OpenAI-compatible API at http://localhost:9337/v1. Start one node, add more nodes later, and let the mesh decide whether a model runs locally, routes to a peer, or uses Skippy stage splits for models that are too large for one box.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Friends Don&#39;t Let Friends Use Ollama</title>
      <link>https://www.zdenek-jurman.cz/posts/dont-use-ollama/</link>
      <pubDate>Wed, 15 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://www.zdenek-jurman.cz/posts/dont-use-ollama/</guid>
      <description>&lt;p&gt;Ollama is the most popular way to run local LLMs. It shouldn’t be. It gained that position by being first, the first tool that made llama.cpp accessible to people who didn’t want to compile C++ or write their own server configs. That was a real contribution, briefly. But the project has since spent years systematically obscuring where its actual technology comes from, misleading users about what they’re running, and drifting from the local-first mission that earned it trust in the first place. All while taking venture capital money.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
