<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLMs on AI VOID</title><link>https://ai-blog.noorshomelab.dev/categories/llms/</link><description>Recent content in LLMs on AI VOID</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 20 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://ai-blog.noorshomelab.dev/categories/llms/index.xml" rel="self" type="application/rss+xml"/><item><title>The Core of LLM Intelligence: What is Context Engineering?</title><link>https://ai-blog.noorshomelab.dev/context-engineering-guide/llm-context-engineering-introduction/</link><pubDate>Fri, 20 Mar 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/context-engineering-guide/llm-context-engineering-introduction/</guid><description>&lt;h2 id="the-core-of-llm-intelligence-what-is-context-engineering"&gt;The Core of LLM Intelligence: What is Context Engineering?&lt;/h2&gt;
&lt;p&gt;Welcome to the exciting world of Context Engineering! If you&amp;rsquo;ve been working with Large Language Models (LLMs), you&amp;rsquo;ve likely experienced their incredible power, but perhaps also some of their quirks. Sometimes they give brilliant answers, and other times they seem to miss the mark, hallucinate, or simply run out of steam. This is where Context Engineering steps in.&lt;/p&gt;
&lt;p&gt;In this chapter, we&amp;rsquo;ll embark on a journey to understand what Context Engineering is, why it&amp;rsquo;s absolutely crucial for building robust and reliable LLM applications, and how it differs from (and complements!) prompt engineering. We&amp;rsquo;ll lay the foundational concepts that will empower you to design more intelligent, efficient, and cost-effective AI systems. Get ready to unlock the true potential of LLMs by mastering the art of providing them with the right information, at the right time, in the right way.&lt;/p&gt;</description></item><item><title>Breaking Down Information: Smart Chunking Strategies</title><link>https://ai-blog.noorshomelab.dev/context-engineering-guide/smart-chunking-strategies/</link><pubDate>Fri, 20 Mar 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/context-engineering-guide/smart-chunking-strategies/</guid><description>&lt;h2 id="breaking-down-information-smart-chunking-strategies"&gt;Breaking Down Information: Smart Chunking Strategies&lt;/h2&gt;
&lt;p&gt;Welcome back, future Context Engineering expert! In our previous chapters, we&amp;rsquo;ve explored the critical concept of the LLM context window and the art of designing and structuring information to fit within it. We&amp;rsquo;ve learned that feeding the right information to an LLM is paramount for high-quality, relevant outputs.&lt;/p&gt;
&lt;p&gt;But what happens when your source material – a massive legal document, a comprehensive research paper, or an entire codebase – far exceeds the LLM&amp;rsquo;s context window? That&amp;rsquo;s where &lt;strong&gt;chunking&lt;/strong&gt; comes into play!&lt;/p&gt;</description></item></channel></rss>