<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Mlops on Bits, Trades &amp; Systems</title>
    <link>https://blog.turboawesome.win/tags/mlops/</link>
    <description>Recent content in Mlops on Bits, Trades &amp; Systems</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 14 May 2024 14:22:00 +0000</lastBuildDate>
    <atom:link href="https://blog.turboawesome.win/tags/mlops/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Evaluating LLM Applications: Why &#39;It Looks Good&#39; Is Not Enough</title>
      <link>https://blog.turboawesome.win/2024/05/evaluating-llm-applications-why-it-looks-good-is-not-enough/</link>
      <pubDate>Tue, 14 May 2024 14:22:00 +0000</pubDate>
      <guid>https://blog.turboawesome.win/2024/05/evaluating-llm-applications-why-it-looks-good-is-not-enough/</guid>
      <description>LLM applications fail in ways that traditional software testing doesn&amp;#39;t catch. Building evaluation frameworks that give you real signal about quality — before and after deployment — is the engineering challenge that separates serious AI products from demos.</description>
    </item>
  </channel>
</rss>
