<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Benchmark on Mike&#39;s Shiny Objects</title>
    <link>https://mikesshinyobjects.tech/tags/benchmark/</link>
    <description>Recent content in Benchmark on Mike&#39;s Shiny Objects</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 03 Apr 2026 10:00:00 +0000</lastBuildDate>
    <atom:link href="https://mikesshinyobjects.tech/tags/benchmark/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>I Benchmarked 10 AI Models for Email Triage — A Free Local Model Won</title>
      <link>https://mikesshinyobjects.tech/posts/2026/2026-04-03-email-triage-local-model-wins/</link>
      <pubDate>Fri, 03 Apr 2026 10:00:00 +0000</pubDate>
      <guid>https://mikesshinyobjects.tech/posts/2026/2026-04-03-email-triage-local-model-wins/</guid>
      <description>&lt;p&gt;&lt;em&gt;This post was written with AI assistance (Claude) for structure and formatting. The analysis, opinions, and surprise at the results are entirely my own.&lt;/em&gt;&lt;/p&gt;&#xA;&lt;hr&gt;&#xA;&lt;p&gt;I built an email triage system that reads incoming mail and classifies it into categories: BULK, ACTION, BILLING, MONITOR, JUNK, and PERSONAL. Each email gets a category, a confidence score, and a one-line reason. The system then labels or files the email accordingly.&lt;/p&gt;&#xA;&lt;blockquote&gt;&#xA;&lt;p&gt;&lt;strong&gt;I expected an expensive cloud model to win.&lt;/strong&gt;&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
