<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Model Calibration on Amit Naik</title>
    <link>https://amitnaik.com/tags/model-calibration/</link>
    <description>Recent content in Model Calibration on Amit Naik</description>
    <generator>Hugo -- 0.144.2</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 28 Sep 2026 09:00:00 -0700</lastBuildDate>
    <atom:link href="https://amitnaik.com/tags/model-calibration/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Calibrating Jev with examples</title>
      <link>https://amitnaik.com/til/2026-09-28-calibrating-jev-with-examples/</link>
      <pubDate>Mon, 28 Sep 2026 09:00:00 -0700</pubDate>
      <guid>https://amitnaik.com/til/2026-09-28-calibrating-jev-with-examples/</guid>
      <description>Seth Kimmel introduces jev-align, an open-source CLI that uses GEPA to align Jev with a user&amp;#39;s decision criteria. The useful distinction is between a general model&amp;#39;s capabilities and the specific examples that define acceptable decisions for a particular application.</description>
    </item>
    <item>
      <title>Laya: a local classifier alternative</title>
      <link>https://amitnaik.com/til/2026-09-28-laya-a-local-classifier-alternative/</link>
      <pubDate>Mon, 28 Sep 2026 08:59:59 -0700</pubDate>
      <guid>https://amitnaik.com/til/2026-09-28-laya-a-local-classifier-alternative/</guid>
      <description>This bookmark points to Laya, an open-weight classifier presented as a locally runnable alternative to Jev. It is a useful candidate to evaluate when classification needs to stay inside your own infrastructure; the post is an introduction, not a comparative benchmark.</description>
    </item>
  </channel>
</rss>
