<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>LaplacianMind Writing</title>
  <id>https://laplacianmind.com/blog/</id>
  <link href="https://laplacianmind.com/blog/"/>
  <link rel="self" href="https://laplacianmind.com/blog/feed.xml"/>
  <updated>2026-10-05T00:00:00Z</updated>
  <entry>
    <title>You are the grader</title>
    <id>https://laplacianmind.com/blog/you-are-the-grader/</id>
    <link href="https://laplacianmind.com/blog/you-are-the-grader/"/>
    <published>2026-10-05T00:00:00Z</published>
    <updated>2026-10-05T00:00:00Z</updated>
    <author><name>Utkarsh</name></author>
    <summary>How frontier language models are post-trained in 2026: the practice loop, where it leaks, the line built around it, and what that means when you hand a model a task.</summary>
  </entry>
</feed>
