<?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 orndorff.dev</title>
    <link>https://orndorff.dev/categories/llm/</link>
    <description>Recent content in Llm on orndorff.dev</description>
    <generator>Hugo -- 0.138.0</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 01 Nov 2025 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://orndorff.dev/categories/llm/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Building a Non-Deterministic Merge Game with LLMs</title>
      <link>https://orndorff.dev/posts/projects/llm-alchemy-game/</link>
      <pubDate>Sat, 01 Nov 2025 00:00:00 +0000</pubDate>
      <guid>https://orndorff.dev/posts/projects/llm-alchemy-game/</guid>
      <description>&lt;h2 id=&#34;what-i-built-and-why&#34;&gt;What I Built and Why&lt;/h2&gt;
&lt;p&gt;I&amp;rsquo;ve always enjoyed those element-combining merge games like Doodle God or Little Alchemy. You know the ones - Water + Fire = Steam, Earth + Water = Mud, that sort of thing. There&amp;rsquo;s something satisfying about discovering combinations, but after playing a few, I started noticing a fundamental limitation: every combination is pre-determined. Everyone who plays gets exactly the same results. The discovery phase is fun, but once you know the combinations, there&amp;rsquo;s no variance.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
