<?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>Llm on Agoston Fung</title>
    <link>/tags/llm/</link>
    <description>Recent content in Llm on Agoston Fung</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Sun, 29 Mar 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="/tags/llm/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>How can an LLM write code?</title>
      <link>/posts/how-can-an-llm-write-code/</link>
      <pubDate>Sun, 29 Mar 2026 00:00:00 +0000</pubDate>
      <guid>/posts/how-can-an-llm-write-code/</guid>
      <description>It can feel like AI is thinking. What&amp;rsquo;s actually happening is closer to pattern recognition - and that frame makes LLMs much easier to reason about.</description>
    </item>
    <item>
      <title>Autocomplete for your personality</title>
      <link>/posts/autocomplete-for-your-personality/</link>
      <pubDate>Tue, 10 Mar 2026 00:00:00 +0000</pubDate>
      <guid>/posts/autocomplete-for-your-personality/</guid>
      <description>Sam Altman said millions are wasted on people thanking LLMs. I keep doing it anyway. Here&amp;rsquo;s why - and what your brain does when you don&amp;rsquo;t.</description>
    </item>
  </channel>
</rss>
