<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>Hooks - Tag - görn.name</title><link>https://g%C3%B6rn.name/tags/hooks/</link><description>Hooks - Tag - görn.name</description><generator>Hugo -- gohugo.io</generator><language>de-DE</language><managingEditor>christoph@goern.name (Christoph Görn)</managingEditor><webMaster>christoph@goern.name (Christoph Görn)</webMaster><copyright>2025 Christoph Görn</copyright><lastBuildDate>Mon, 28 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://g%C3%B6rn.name/tags/hooks/" rel="self" type="application/rss+xml"/><item><title>A model router for Claude Code, and why it should live on my GPU</title><link>https://g%C3%B6rn.name/posts/2026-09-28-claude-code-model-router/</link><pubDate>Mon, 28 Sep 2026 00:00:00 +0000</pubDate><author>christoph@goern.name (Christoph Görn)</author><guid>https://g%C3%B6rn.name/posts/2026-09-28-claude-code-model-router/</guid><description><![CDATA[<p><em>For people running Claude Code who wonder whether a small classifier can send
their prompts to cheaper models. Short answer: a little, with caveats. The
code lives in my private infra repo; the numbers below are from its log.</em></p>
<hr>
<p>My timeline has been full of &ldquo;what Jev can do for you&rdquo; posts. Jev sizes your
request, Jev picks the right model, Jev saves you money. Fine. But every one of
those setups has the same shape: before any work happens, your prompt goes to
someone else&rsquo;s model, just so that model can answer with one word.</p>]]></description></item></channel></rss>