<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Ux on Alexander Junge&#39;s website</title>
    <link>https://www.alexanderjunge.net/tags/ux/</link>
    <description>Recent content in Ux on Alexander Junge&#39;s website</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-US</language>
    <lastBuildDate>Sat, 23 Mar 2024 00:00:00 +0000</lastBuildDate>
    
	<atom:link href="https://www.alexanderjunge.net/tags/ux/index.xml" rel="self" type="application/rss+xml" />
    
    
    <item>
      <title>RAG 2.0?</title>
      <link>https://www.alexanderjunge.net/blog/rag20maybe/</link>
      <pubDate>Sat, 23 Mar 2024 00:00:00 +0000</pubDate>
      
      <guid>https://www.alexanderjunge.net/blog/rag20maybe/</guid>
      <description>This blog post on &amp;ldquo;RAG 2.0&amp;rdquo; by Contextual AI got me thinking. Not sure, if it makes sense for anyone to be &amp;ldquo;announcing&amp;rdquo; (or even defining) RAG 2.0 but there are a few tidbits in this post hinting towards a potentially more powerful, general approach to RAG they are working on. The article is light on technical details and heavy on claimed &amp;ldquo;state-of-the-art&amp;rdquo; results on various benchmarks.
However, I very much agree that a) defining evaluation datasets first, and b) then end-to-end optimizing RAG performance is the right approach to improve (pre-)production systems.</description>
    </item>
    
  </channel>
</rss>