
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>/var/log/mattia</title>
      <link>https://mattiaperetti.it/blog</link>
      <description>Senior backend engineer writing about backend architecture, application security, and the shift toward agentic AI systems.</description>
      <language>en-us</language>
      <managingEditor>undefined (Mattia Peretti)</managingEditor>
      <webMaster>undefined (Mattia Peretti)</webMaster>
      <lastBuildDate>Tue, 07 Jul 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://mattiaperetti.it/tags/llm/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://mattiaperetti.it/blog/okf-and-the-two-brains-of-an-llm-agent</guid>
    <title>OKF and the Two Brains of an LLM Agent</title>
    <link>https://mattiaperetti.it/blog/okf-and-the-two-brains-of-an-llm-agent</link>
    <description>Google quietly published OKF, a plain markdown-plus-frontmatter format for agent knowledge, built on a pattern Karpathy sketched in a gist months earlier. Working through both taught me to stop thinking of an LLM as one brain and start thinking of it as two.</description>
    <pubDate>Tue, 07 Jul 2026 00:00:00 GMT</pubDate>
    <author>undefined (Mattia Peretti)</author>
    <category>ai</category><category>agentic-ai</category><category>llm</category><category>memory</category><category>okf</category>
  </item>

    </channel>
  </rss>
