
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Articles by Dan Orlando</title>
      <link>https://danorlando.com/blog</link>
      <description>How-to&#39;s, discoveries and other useful nuggets fit for developer consumption.</description>
      <language>en-us</language>
      <managingEditor>undefined (Dan Orlando)</managingEditor>
      <webMaster>undefined (Dan Orlando)</webMaster>
      <lastBuildDate>Thu, 16 Apr 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://danorlando.com/tags/rag/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://danorlando.com/blog/genai/retrieval-as-generation</guid>
    <title>Retrieval as Generation: The Architecture That Kills External Orchestrators</title>
    <link>https://danorlando.com/blog/genai/retrieval-as-generation</link>
    <description>An 8B-parameter model matches GPT-4o across five knowledge-intensive benchmarks and beats it on two. It does this by replacing the entire retrieval orchestration layer—confidence classifiers, query routers, rerankers, fusion logic—with four special tokens. No external components. When it fails, you read a transcript. That&#39;s the whole debugging story.</description>
    <pubDate>Thu, 16 Apr 2026 00:00:00 GMT</pubDate>
    <author>undefined (Dan Orlando)</author>
    <category>generativeai</category><category>rag</category><category>architecture</category><category>systemdesign</category><category>agentsystems</category><category>agenticai</category>
  </item>

  <item>
    <guid>https://danorlando.com/blog/genai/why-your-rag-is-obsolete</guid>
    <title>Why Your RAG Is Already Obsolete (And What Works Instead)</title>
    <link>https://danorlando.com/blog/genai/why-your-rag-is-obsolete</link>
    <description>If your RAG pipeline runs the same retrieval strategy for every query, you&#39;re in one corner of a five-dimensional design space—and it&#39;s the worst-performing corner. Static pipelines leave up to 15% accuracy on the table and spend 3x the tokens they need to. The move to agentic retrieval is incremental, and each step compounds with every model generation.</description>
    <pubDate>Sat, 18 Apr 2026 00:00:00 GMT</pubDate>
    <author>undefined (Dan Orlando)</author>
    <category>generativeai</category><category>rag</category><category>architecture</category><category>systemdesign</category><category>agentsystems</category><category>agenticai</category>
  </item>

    </channel>
  </rss>
