<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Technology on AI VOID</title><link>https://ai-blog.noorshomelab.dev/categories/technology/</link><description>Recent content in Technology on AI VOID</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 30 Jan 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://ai-blog.noorshomelab.dev/categories/technology/index.xml" rel="self" type="application/rss+xml"/><item><title>AI All Around Us: Real-World Stories</title><link>https://ai-blog.noorshomelab.dev/ai-ml-journey-2026/ai-everywhere-examples/</link><pubDate>Sun, 18 Jan 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/ai-ml-journey-2026/ai-everywhere-examples/</guid><description>&lt;p&gt;Hello, future AI explorer! 👋&lt;/p&gt;
&lt;p&gt;Welcome back! In our last chapters, we started our exciting journey into the world of Artificial Intelligence (AI) and Machine Learning (ML). We talked about what these big words mean in simple terms, like computers learning from experience, just like you and I do. We also touched upon the idea of &amp;ldquo;data&amp;rdquo; as the fuel for this learning. You&amp;rsquo;re doing an amazing job grasping these foundational ideas!&lt;/p&gt;</description></item><item><title>Chapter 11: AI in Action: Real-World Use Cases and Impact</title><link>https://ai-blog.noorshomelab.dev/ai-ml-journey-2026/ai-real-world-use-cases/</link><pubDate>Sun, 18 Jan 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/ai-ml-journey-2026/ai-real-world-use-cases/</guid><description>&lt;h2 id="chapter-11-ai-in-action-real-world-use-cases-and-impact"&gt;Chapter 11: AI in Action: Real-World Use Cases and Impact&lt;/h2&gt;
&lt;h3 id="welcome-to-chapter-11"&gt;Welcome to Chapter 11!&lt;/h3&gt;
&lt;p&gt;In our previous chapters, we&amp;rsquo;ve laid the groundwork for understanding Artificial Intelligence (AI) and Machine Learning (ML). We&amp;rsquo;ve explored what data is, how models learn patterns, and the fundamental concepts of training, prediction, and evaluation. You&amp;rsquo;ve even dipped your toes into some basic programming ideas!&lt;/p&gt;
&lt;p&gt;Now, it&amp;rsquo;s time for the exciting part: seeing how all these pieces come together to create the incredible AI applications that are shaping our world right now. This chapter isn&amp;rsquo;t just about theory; it&amp;rsquo;s about connecting those theories to the practical, sometimes magical, things AI does every single day.&lt;/p&gt;</description></item><item><title>Chapter 13: OpenZL Alternatives and When to Use Them</title><link>https://ai-blog.noorshomelab.dev/openzl-mastery-2026/13-alternatives/</link><pubDate>Mon, 26 Jan 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/openzl-mastery-2026/13-alternatives/</guid><description>&lt;h2 id="introduction-navigating-the-world-of-data-compression"&gt;Introduction: Navigating the World of Data Compression&lt;/h2&gt;
&lt;p&gt;Welcome to Chapter 13! So far, you&amp;rsquo;ve learned that OpenZL is a powerful, flexible framework designed to revolutionize how we compress &lt;em&gt;structured data&lt;/em&gt;. We&amp;rsquo;ve explored its core concepts, set up an environment, and even tackled practical examples. But here&amp;rsquo;s a crucial truth in the world of technology: no single tool is a silver bullet for every problem.&lt;/p&gt;
&lt;p&gt;In this chapter, we&amp;rsquo;ll broaden our perspective and look at OpenZL within the larger ecosystem of data compression. We&amp;rsquo;ll explore various alternatives, understand their underlying principles, and, most importantly, learn &lt;em&gt;when&lt;/em&gt; to choose OpenZL versus when another solution might be a better fit. This knowledge will empower you to make informed decisions for your data compression needs, ensuring efficiency and optimal performance.&lt;/p&gt;</description></item><item><title>The Future of AI &amp;amp; Your Place in It</title><link>https://ai-blog.noorshomelab.dev/ai-ml-journey-2026/ai-future-and-careers/</link><pubDate>Sun, 18 Jan 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/ai-ml-journey-2026/ai-future-and-careers/</guid><description>&lt;p&gt;Hello, future AI explorer! You&amp;rsquo;ve made it to the final chapter of our beginner&amp;rsquo;s journey. Give yourself a huge pat on the back – that&amp;rsquo;s a fantastic achievement! You started with zero programming experience and now have a solid conceptual understanding of what AI and Machine Learning are, how they learn, and how they make predictions. You even dipped your toes into some basic coding and played with real AI tools!&lt;/p&gt;</description></item><item><title>Chapter 17: Ethical Considerations and Responsible AI in Post-Training</title><link>https://ai-blog.noorshomelab.dev/tunix-mastery-2026/17-ethical-ai/</link><pubDate>Fri, 30 Jan 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/tunix-mastery-2026/17-ethical-ai/</guid><description>&lt;h2 id="chapter-17-ethical-considerations-and-responsible-ai-in-post-training"&gt;Chapter 17: Ethical Considerations and Responsible AI in Post-Training&lt;/h2&gt;
&lt;p&gt;Welcome to Chapter 17! So far, we&amp;rsquo;ve explored the immense power of Tunix for fine-tuning Large Language Models (LLMs), optimizing their performance, and tailoring them for specific tasks. As we wield such powerful tools, it&amp;rsquo;s crucial to pause and consider the broader impact of the AI systems we build. This chapter shifts our focus from pure technical implementation to the vital domain of ethical considerations and responsible AI in the post-training lifecycle.&lt;/p&gt;</description></item><item><title>What makes an AI system an &amp;#34;agent&amp;#34;?</title><link>https://ai-blog.noorshomelab.dev/agentic-design-patern-ebook/chapters/what-makes-an-ai-system-an-agent/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/agentic-design-patern-ebook/chapters/what-makes-an-ai-system-an-agent/</guid><description>&lt;h1 id="what-makes-an-ai-system-an-agent"&gt;What makes an AI system an Agent?&lt;/h1&gt;
&lt;p&gt;In simple terms, an &lt;strong&gt;AI agent&lt;/strong&gt; is a system designed to perceive its environment and take actions to achieve a specific goal. It&amp;rsquo;s an evolution from a standard Large Language Model (LLM), enhanced with the abilities to plan, use tools, and interact with its surroundings. Think of an Agentic AI as a smart assistant that learns on the job. It follows a simple, five-step loop to get things done (see Fig.1):&lt;/p&gt;</description></item><item><title>How DRM for Web Video Streaming Works: Deep Dive into Internals</title><link>https://ai-blog.noorshomelab.dev/how-it-works/how-drm-web-video-streaming-works/</link><pubDate>Sun, 11 Jan 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/how-it-works/how-drm-web-video-streaming-works/</guid><description>&lt;h2 id="introduction"&gt;Introduction&lt;/h2&gt;
&lt;p&gt;In the age of ubiquitous online video, consumers expect seamless access to a vast library of films, TV shows, and live events. Behind the scenes, ensuring this content is delivered securely and according to the rights granted by its creators is a complex, multi-layered system known as Digital Rights Management (DRM). For web video streaming, DRM is the invisible guardian that protects premium content from unauthorized copying and distribution.&lt;/p&gt;</description></item></channel></rss>