<?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>classic on Sparse Notes</title>
    <link>https://sparsenotes.com/tags/classic/</link>
    <description>Recent content in classic 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, 23 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://sparsenotes.com/tags/classic/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Let&#39;s Build GPT From Scratch: Karpathy&#39;s Classic, Re-read in 2026</title>
      <link>https://sparsenotes.com/posts/2026/05/karpathy-lets-build-gpt/</link>
      <pubDate>Sat, 23 May 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/05/karpathy-lets-build-gpt/</guid>
      <description>Notes on Andrej Karpathy&amp;#39;s 2023 classic &amp;#39;Let&amp;#39;s build GPT: from scratch, in code, spelled out.&amp;#39; — tokenization, the bigram baseline, the math of self-attention, multi-head, residual &#43; layernorm, and how the same ~200 lines scale to a real GPT.</description>
    </item>
    
  </channel>
</rss>
