
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Omers playground</title>
      <link>https://omeratagun.net/blog</link>
      <description>A personal blog that contains tech related stuff</description>
      <language>en-us</language>
      <managingEditor>omratagn@gmail.com (Omer ATAGUN)</managingEditor>
      <webMaster>omratagn@gmail.com (Omer ATAGUN)</webMaster>
      <lastBuildDate>Fri, 04 Sep 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://omeratagun.net/tags/automation/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://omeratagun.net/blog/cameras-local-llm-wrong-assumptions</guid>
    <title>Cameras, a local LLM, and a pile of wrong assumptions</title>
    <link>https://omeratagun.net/blog/cameras-local-llm-wrong-assumptions</link>
    <description>I pointed a spare 3090 at four cameras and a house full of Home Assistant entities to build a fully local NVR with a local voice assistant. Most of what I assumed going in turned out to be wrong. Here is what actually held up.</description>
    <pubDate>Fri, 04 Sep 2026 00:00:00 GMT</pubDate>
    <author>omratagn@gmail.com (Omer ATAGUN)</author>
    <category>home server</category><category>self hosted</category><category>frigate</category><category>nvr</category><category>home assistant</category><category>ollama</category><category>local ai</category><category>computer vision</category><category>automation</category><category>HA</category>
  </item>

    </channel>
  </rss>
