<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
  xmlns:content="http://purl.org/rss/1.0/modules/content/"
  xmlns:atom="http://www.w3.org/2005/Atom"
  xmlns:dc="http://purl.org/dc/elements/1.1/"
>
  <channel>
    <title>Kabir Murjani — Writing</title>
    <link>https://kabir.codes</link>
    <description>Technical essays on machine learning, optimization, combinatorial search, and intelligent systems by Kabir Murjani.</description>
    <language>en-us</language>
    <managingEditor>kabir.murjani@iimb.ac.in (Kabir Murjani)</managingEditor>
    <webMaster>kabir.murjani@iimb.ac.in (Kabir Murjani)</webMaster>
    <lastBuildDate>Fri, 05 Jun 2026 03:50:04 GMT</lastBuildDate>
    <atom:link href="https://kabir.codes/rss.xml" rel="self" type="application/rss+xml" />
    <image>
      <url>https://kabir.codes/Of_H.jpg</url>
      <title>Kabir Murjani — Writing</title>
      <link>https://kabir.codes</link>
    </image>

    <item>
      <title>Dreaming in Proofs</title>
      <link>https://kabir.codes/writing/dreaming</link>
      <guid isPermaLink="true">https://kabir.codes/writing/dreaming</guid>
      <pubDate>Sun, 01 Mar 2026 00:00:00 GMT</pubDate>
      <description>Novelty is not a better optimizer. It is a wild dreamer chained to a merciless judge.</description>
      <content:encoded><![CDATA[
        <p><strong>Abstract:</strong> Here is something I have come to believe after staring at search problems for too long: optimization cannot be creative. Not "is bad at being creative." *Cannot be.* It is the wrong kind of process.</p>
        <p><a href="https://kabir.codes/writing/dreaming">Read the full article →</a></p>
        <img src="https://kabir.codes/blog-2.jpg" alt="Dreaming in Proofs" />
      ]]></content:encoded>
      <author>kabir.murjani@iimb.ac.in (Kabir Murjani)</author>
      <category>Machine Learning</category>
    </item>
  </channel>
</rss>