How Large Language Models Work

<p><strong>Learn how large language models like GPT and Gemini work under the hood in plain English.</strong><br><br><em>How Large Language Models Work</em> translates years of expert research on Large Language Models into a readable, focused introduction to working with these amazing systems. It explains clearly how LLMs function, introduces the optimization techniques to fine-tune them, and shows how to create pipelines and processes to ensure your AI applications are efficient and error-free.<br><br>In <em>How Large Language Models Work</em> you will learn how to:<br><br></p> <ul> <li>Test and evaluate LLMs</li> <li>Use human feedback, supervised fine-tuning, and Retrieval augmented generation (RAG)</li> <li>Reducing the risk of bad outputs, high-stakes errors, and automation bias</li> <li>Human-computer interaction systems</li> <li>Combine LLMs with traditional ML</li> </ul> <p><br><em>How Large Language Models Work</em> is written by some of the best machine learning researchers at Booz Allen Hamilton, including researcher <strong>Stella Biderman</strong>, Director of AI/ML Research <strong>Drew Farris</strong>, and Director of Emerging AI <strong>Edward Raff</strong>. In clear and simple terms, these experts lay out the foundational concepts of LLMs, the technology’s opportunities and limitations, and best practices for incorporating AI into your organization.</p>