<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Latency on Subhajai Benchadhikul</title><link>https://subhajai.benchadhikul.com/tags/latency/</link><description>Recent content in Latency on Subhajai Benchadhikul</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 15 Jul 2026 07:00:00 +0700</lastBuildDate><atom:link href="https://subhajai.benchadhikul.com/tags/latency/index.xml" rel="self" type="application/rss+xml"/><item><title>Semantic Caching: The Cheapest AI Answer Is the One You Don't Regenerate</title><link>https://subhajai.benchadhikul.com/posts/2026-07-15-technology-semantic-caching-ai/</link><pubDate>Wed, 15 Jul 2026 07:00:00 +0700</pubDate><guid>https://subhajai.benchadhikul.com/posts/2026-07-15-technology-semantic-caching-ai/</guid><description>Traditional caches only recognise a question they&amp;rsquo;ve seen letter for letter. Semantic caching recognises meaning — and for the thousandth shopper asking &amp;lsquo;does this run small?&amp;rsquo; in slightly different words, that difference is most of your bill.</description></item></channel></rss>