about this book
How Large Language Models Work is the culmination of countless hours of research, explorations, conversations, and building and evaluating large language models and the systems that use them to solve problems. It is a distillation of years of working in the fields of machine learning, natural language processing, and software engineering that we, the authors, bring to the table. It’s important to us to share what we’ve learned and break down the complexities of the field into a straightforward conversation that presents foundational details on how LLMs work and builds from there to cover topics that are not widely understood. We seek to dispel some myths and shed light on the realities along the way.
This book does not describe how to implement LLMs like ChatGPT using code. Instead, it covers the foundational concepts that make LLMs operate, as well as the opportunities and limitations of this technology. We’ll provide you with an understanding of how the underlying algorithms operate. As a result, you’ll better understand why LLMs are implemented the way they are and how LLMs can be used to solve a variety of problems. Our goal is to translate years of LLM research into something understandable for someone new to the field.