<?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>Query-Optimization on Kent Yao</title>
    <link>https://yaooqinn.github.io/tags/query-optimization/</link>
    <description>Recent content in Query-Optimization on Kent Yao</description>
    <generator>Hugo -- 0.157.0</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 27 May 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://yaooqinn.github.io/tags/query-optimization/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>LLMs Shouldn&#39;t Replace the Query Optimizer — They Should Sit Behind It</title>
      <link>https://yaooqinn.github.io/posts/query-engines/llm-as-plan-tuner-not-optimizer/</link>
      <pubDate>Wed, 27 May 2026 00:00:00 +0000</pubDate>
      <guid>https://yaooqinn.github.io/posts/query-engines/llm-as-plan-tuner-not-optimizer/</guid>
      <description>Putting the LLM after the optimizer, emitting JSON patches for local plan tuning, is easier to reason about as engineering than asking it to replace the cost-based optimizer.</description>
    </item>
  </channel>
</rss>
