<?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>post-training on Sparse Notes</title>
    <link>https://sparsenotes.com/tags/post-training/</link>
    <description>Recent content in post-training on Sparse Notes</description>
    <image>
      <url>https://sparsenotes.com/images/og-default.png</url>
      <link>https://sparsenotes.com/images/og-default.png</link>
    </image>
    <generator>Hugo -- gohugo.io</generator>
    <lastBuildDate>Sat, 13 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://sparsenotes.com/tags/post-training/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Running 128 Coding Agents at Once: Inside Cursor, Pause AI, and the Era of Agent Maxing</title>
      <link>https://sparsenotes.com/posts/2026/06/cursor-running-128-coding-agents/</link>
      <pubDate>Sat, 13 Jun 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/06/cursor-running-128-coding-agents/</guid>
      <description>A Cursor engineer and the founders of Pause AI compare notes on running dozens of parallel coding agents, building post-trained &amp;#39;main agents,&amp;#39; thermonuclear review loops, and what comes after vanilla-ice-cream frontier models.</description>
    </item>
    
  </channel>
</rss>
