<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>Constantinos Orphanides · writing</title>
  <id>https://www.constantinosorphanides.com/writing/feed.xml</id>
  <updated>2026-09-29T22:50:00+03:00</updated>
  <author><name>Constantinos Orphanides</name></author>
  <link rel="self" href="https://www.constantinosorphanides.com/writing/feed.xml"/>
  <link rel="alternate" href="https://www.constantinosorphanides.com/writing/"/>
  <entry>
    <title>How large language models work</title>
    <id>https://www.constantinosorphanides.com/how-large-language-models-work/</id>
    <link rel="alternate" href="https://www.constantinosorphanides.com/how-large-language-models-work/"/>
    <published>2026-08-30T18:40:00+03:00</published>
    <updated>2026-09-29T22:50:00+03:00</updated>
    <summary>What a large language model computes when it answers you, and why its answer is picked rather than derived.</summary>
  </entry>
  <entry>
    <title>Formal concept analysis</title>
    <id>https://www.constantinosorphanides.com/formal-concept-analysis/</id>
    <link rel="alternate" href="https://www.constantinosorphanides.com/formal-concept-analysis/"/>
    <published>2026-07-16T20:30:00+03:00</published>
    <updated>2026-09-20T20:30:00+03:00</updated>
    <summary>What formal concept analysis finds in a table, and how to read a concept lattice.</summary>
  </entry>
</feed>
