<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Bake-Off on Thede Technologies</title><link>https://thedetech.com/tags/bake-off/</link><description>Recent content in Bake-Off on Thede Technologies</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 06 Aug 2026 19:08:20 -0500</lastBuildDate><atom:link href="https://thedetech.com/tags/bake-off/index.xml" rel="self" type="application/rss+xml"/><item><title>Can a Local Model Read My Inbox? A Bake-off</title><link>https://thedetech.com/lab/2026-06-27-local-model-bakeoff-email-enrichment/</link><pubDate>Sat, 27 Jun 2026 00:00:00 +0000</pubDate><guid>https://thedetech.com/lab/2026-06-27-local-model-bakeoff-email-enrichment/</guid><description>&lt;p>How much of my daily AI work actually needs to leave my machine? The frontier models still win the hard, open-ended thinking. But most of my real workload isn&amp;rsquo;t that - it&amp;rsquo;s repetitive, high-volume, and touches data I&amp;rsquo;d rather keep home: my mail, my documents, decades of personal history.&lt;/p>
&lt;p>Email was the perfect test. I was building a system that reads my inbox for me - each message becomes a small structured record, so a daily brief can be written from records instead of raw mail. That per-message reading should run locally, if local is good enough.&lt;/p></description></item></channel></rss>