<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel>
  <title>Artifipedia Blog</title>
  <link>https://artifipedia.com/blog</link>
  <description>Guides, comparisons, and explainers on artificial intelligence.</description>
  <language>en-us</language>
  <item>
    <title>How to read a model release</title>
    <link>https://artifipedia.com/blog/how-to-read-a-model-release</link>
    <guid>https://artifipedia.com/blog/how-to-read-a-model-release</guid>
    <pubDate>Wed, 15 Jul 2026 00:00:00 GMT</pubDate>
    <description>Every few weeks a lab announces a new frontier model and every headline says the same thing. Here's how to work out what actually changed, what the benchmark numbers mean, and which parts of the announcement are marketing.</description>
  </item>
  <item>
    <title>Your RAG system isn't hallucinating. It never found the answer.</title>
    <link>https://artifipedia.com/blog/rag-retrieval-not-generation</link>
    <guid>https://artifipedia.com/blog/rag-retrieval-not-generation</guid>
    <pubDate>Wed, 15 Jul 2026 00:00:00 GMT</pubDate>
    <description>When a RAG system gives a bad answer, almost everyone blames the model. Usually the right passage was never retrieved — and that changes everything about how you fix it.</description>
  </item>
  <item>
    <title>RAG vs. Fine-tuning: which should you actually use?</title>
    <link>https://artifipedia.com/blog/rag-vs-fine-tuning</link>
    <guid>https://artifipedia.com/blog/rag-vs-fine-tuning</guid>
    <pubDate>Fri, 10 Jul 2026 00:00:00 GMT</pubDate>
    <description>The two most common ways to make a general AI model work on your problem — why the choice is simpler than it looks, why almost everyone gets it wrong in the same direction, and what to try before you touch either.</description>
  </item>
</channel></rss>