<?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 franfabrizio.dev</title>
    <link>http://franfabrizio.dev/tags/llm/</link>
    <description>Recent content in llm on franfabrizio.dev</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 23 Oct 2026 00:00:00 -0700</lastBuildDate>
    <atom:link href="http://franfabrizio.dev/tags/llm/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Trimming MCP Tool Context Bloat</title>
      <link>http://franfabrizio.dev/posts/trimming-mcp-tool-context-bloat/</link>
      <pubDate>Fri, 23 Oct 2026 00:00:00 -0700</pubDate>
      <guid>http://franfabrizio.dev/posts/trimming-mcp-tool-context-bloat/</guid>
      <description>&lt;p&gt;One of the ways to close the performance gap between local LLMs and frontier models is to give local LLMs access to your private data that you either don&amp;rsquo;t feel comfortable giving to commercial providers or where it would simply be impractical to do so. I&amp;rsquo;m talking about sources of data like your personal notes, your financial documents, your health records, your home automation systems, and similar data that can give LLMs the context they need to become truly useful in your day-to-day life.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
