<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>RAG on Signal &amp; Syntax</title><link>https://signal-and-syntax.com/tags/rag/</link><description>Recent content in RAG on Signal &amp; Syntax</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 09 Feb 2026 06:00:00 -0700</lastBuildDate><atom:link href="https://signal-and-syntax.com/tags/rag/index.xml" rel="self" type="application/rss+xml"/><item><title>How Large Language Models (LLMs) Know Things They Were Never Taught</title><link>https://signal-and-syntax.com/posts/how-large-language-models-know-things-they-were-never-taught/</link><pubDate>Mon, 09 Feb 2026 06:00:00 -0700</pubDate><guid>https://signal-and-syntax.com/posts/how-large-language-models-know-things-they-were-never-taught/</guid><description>When you ask an LLM without web search enabled a question like &amp;ldquo;What happened in the news this morning?&amp;rdquo;, the LLM will respond by telling you that it doesn&amp;rsquo;t have access to current events and suggest you check a more current news source such as Reuters or Google News.
Conversely, ask an LLM with web search enabled the same question, and you receive a detailed rundown of breaking stories, political controversies, and sports news from the past 24 hours.</description></item></channel></rss>