<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Llm on @zhisme :: signal over noise</title><link>https://zhisme.com/tags/llm/</link><description>Recent content in Llm on @zhisme :: signal over noise</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 15 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://zhisme.com/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Decision models. Is determinism great again?</title><link>https://zhisme.com/articles/decision-models/</link><pubDate>Thu, 15 Oct 2026 00:00:00 +0000</pubDate><guid>https://zhisme.com/articles/decision-models/</guid><description>&lt;h2 id="what-is-a-decision-model"&gt;What is a decision model?&lt;/h2&gt;&#10;&lt;p&gt;If you&amp;rsquo;ve never heard the term, don&amp;rsquo;t worry &amp;ndash; it&amp;rsquo;s simpler than it sounds.&lt;/p&gt;&#10;&lt;p&gt;An LLM takes text and gives you text back. You ask a question, it writes an answer, word by word. Ask the same question twice and the wording, the structure, sometimes even the conclusion will drift. Your code then has to read that answer and guess what it meant.&lt;/p&gt;&#10;&lt;p&gt;So the difference in one line: an LLM answers in prose, a decision model answers in data.&lt;/p&gt;</description></item></channel></rss>