<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>Posts on meowy</title>
		<link>https://meowy-site.pages.dev/posts/</link>
		<description>Recent content in Posts on meowy</description>
		<generator>Hugo</generator>
		<language>en-us</language>
		
		
		
		
			<lastBuildDate>Fri, 29 May 2026 00:00:00 +0000</lastBuildDate>
		
			<atom:link href="https://meowy-site.pages.dev/posts/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>What RAG actually is</title>
				<link>https://meowy-site.pages.dev/posts/what-rag-actually-is/</link>
				<pubDate>Fri, 29 May 2026 00:00:00 +0000</pubDate>
				<guid>https://meowy-site.pages.dev/posts/what-rag-actually-is/</guid>
				<description>&lt;p&gt;Nowadays LLMs are like superintelligent ai heroes that can understand and help you with everything from writing to coding. But most LLMs are frozen in time, think of like an isekai-ed hero that&amp;rsquo;s been hit by truck-kun and sent to another world where they&amp;rsquo;re stuck forever. But that hero doesn&amp;rsquo;t know anything about the world and still needs to learn and adapt for the survival of the new world they&amp;rsquo;re sent to.&#xA;Just like that, LLMs are stuck in frozen time also. It doesn&amp;rsquo;t know anything about specific company docs, personal notes, or even worse cause when it doesn&amp;rsquo;t know what it doesn&amp;rsquo;t know, it doesn&amp;rsquo;t stay quiet, it just starts to hallucinate and make up things that are not true. We can definitely fine-tune the model to help us with tasks but that&amp;rsquo;s super slow and expensive to do. And we have to keep doing it every time the data changes.&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
