<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>Jottings of Vishal - entropy</title>
  <link href="https://jottings.vishalvshekkar.com/tags/entropy.html" rel="alternate" />
  <link href="https://jottings.vishalvshekkar.com/tags/entropy/atom.xml" rel="self" type="application/atom+xml" />
  <id>https://jottings.vishalvshekkar.com/tags/entropy/</id>
  <updated>2026-08-13T07:48:17.854Z</updated>
  <subtitle>Posts tagged with "entropy"</subtitle>
  
  <entry>
    <title>LLM watermarking turns the model’s linguistic entropy into bandwidth.</title>
    <link href="https://jottings.vishalvshekkar.com/jots/1769623954.html" rel="alternate" />
    <id>https://jottings.vishalvshekkar.com/jots/1769623954.html</id>
    <updated>2026-08-13T07:48:16.239Z</updated>
    <summary>LLM watermarking turns the model’s linguistic entropy into bandwidth. Wherever the model has multiple plausible ways to say the same thing, those degrees of freedom become a channel through which a hidden (watermarking) signal can be transmitted.</summary>
  </entry>
  
</feed>