A structured collection of articles to guide you from fundamentals to advanced concepts in Large Language Models
Start your journey by understanding the core building blocks of Large Language Models
4 ArticlesA clear, intuitive explanation of how LLMs like GPT-4 and GPT-5 actually work under the hood — with a special focus on the attention mechanism that lets them understand context.
Learn what a neural network is and how it works conceptually. No hard math, just logic.
Peel back the layers of Large Language Models to understand the artificial neuron, the power of ReLU, and how these simple units power the massive Transformer architecture.
What does the '7B' on an LLM really mean? A rigorous breakdown of the Transformer architecture, showing exactly where those billions of parameters come from.
Understand how LLMs process information and the key concepts that power them
5 ArticlesUnderstand how text becomes tokens before it enters a language model.
Explore how temperature changes token probabilities and how it differs from top-p sampling.
Learn what embeddings are, how embedding models create them, how to store and query them efficiently, and what trade-offs to consider when scaling large RAG systems.
Understanding the limitations and capabilities of LLM context windows and how to work with them.
We've explored the intricate architecture of the Transformer model—the billions of parameters that form its brain. But a brain, no matter how powerful, is useless without a nervous system and a life-support machine. That system, in the world of AI, is the inference engine.
Master the art of building intelligent systems that combine retrieval with generation
5 ArticlesUnderstanding Retrieval-Augmented Generation and how it enhances AI systems with external knowledge.
A deep dive into the mechanics of RAG systems and how they retrieve and use information.
Explore the essential components that make up a production-ready RAG system.
Discover how graph-based approaches enhance traditional RAG systems with structured knowledge.
A hands-on tutorial to build your own RAG system from scratch.
Apply your knowledge with real-world concepts and implementation strategies
3 ArticlesWhy shrinking your model is like compressing a JPEG—and how to do it without lobotomizing your AI.
Compare two approaches to customizing LLMs and learn when to use each technique.
Explore Google's Gemini file search capabilities and how they enhance document understanding.
Click on any section card to explore the curated articles and build your understanding step by step