<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Long Context on Subhajai Benchadhikul</title><link>https://subhajai.benchadhikul.com/tags/long-context/</link><description>Recent content in Long Context on Subhajai Benchadhikul</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 02 Oct 2026 09:05:00 +0700</lastBuildDate><atom:link href="https://subhajai.benchadhikul.com/tags/long-context/index.xml" rel="self" type="application/rss+xml"/><item><title>CAG for the Knowledge That Never Changes</title><link>https://subhajai.benchadhikul.com/posts/2026-10-02-cag-for-the-knowledge-that-never-changes/</link><pubDate>Fri, 02 Oct 2026 09:05:00 +0700</pubDate><guid>https://subhajai.benchadhikul.com/posts/2026-10-02-cag-for-the-knowledge-that-never-changes/</guid><description>Cache-Augmented Generation skips retrieval entirely by preloading stable knowledge into the model&amp;rsquo;s context. For the right slice of an e-commerce stack, it is faster and simpler than RAG.</description></item></channel></rss>