Email the Author
You can use this page to email Roger Gullhaug about The inner workings of Large Language Models.
About the Book
Large language models like ChatGPT, Claude, and Copilot are changing the way we work, learn, and build software — but how do they actually work?
If you've ever wondered what goes on under the hood of an LLM, this book is for you. It's written by a developer who decided to go deep — and take careful notes along the way.
This book explains how large language models operate, step by step, using clear language and practical illustrations. Whether you're a software developer, tech enthusiast, or simply curious, you'll come away with a strong intuitive understanding of how these models generate text, learn from data, and represent meaning using mathematics.
You'll learn about:
- Tokenization, embeddings, and vector representations
- The inner workings of self-attention and transformer layers
- How models are trained, fine-tuned, and optimized
- Common myths and misconceptions
- And much more — including how I used LLMs during my research for the book
This isn't an academic text or a deep dive into every research paper — it's a practical, visual, and approachable explanation for people who want to understand LLMs without getting lost in jargon.
If you're ready to move beyond just using AI and start understanding it, this book will give you a solid foundation
About the Author
Roger Gullhaug is Director of Development and Operations at RamBase (Jakob Hatteland Computer AS). He is responsible for a team of 60 developers, architects, testers and devops engineers.
A technologist at heart, he combines two decades of software-development experience with a passion for nurturing people and building high-performing teams.