AI Engineering: Building Applications with Foundation Models

This book is so incredibly well-organized and well-edited that it’s hard to believe it’s a first edition rather than a third or fourth. I love when authors invite readers to jump around and read chapters out of order; in this case, every section proved helpful. This book offers a clear and valuable overview of AI, I plan to keep it close at hand as a reference.

I don't normally have the time for reviews anymore but I had to do one for this book. This book is excellent. The level of detail and range of topics was just right. With some books I've had to force myself to finish. This one kept me interested throughout the entire book and provided everything clearly. I'm more interested in usage of foundation models (LLM's, RAG, etc.) but the chapters on model pre-training/training/evaluation provided great detail. I'm looking forward to more works from Chip.

It's always daunting to pick up a technical book that's over 500 pages long or 21 hours long. However, this book did not disappoint. Not every section, of course, addressed my particular needs. However, the entire treatise was clearly communicated with a broader technical audience in mind. That should be no surprise because Chip Huyen, besides being an AI expert, taught graduate school classes in AI at Stanford and writes science fiction as a side hobby. This book is simply the best technical introduction I've encountered to date. The book starts with high-level concepts about AI, which would be accessible to all sorts of scientific folks. Then it focuses on technical topics that are of most interest to engineers. It does an excellent job of centering around concepts first and not being wedded to particular technologies which will soon change. I valued the insights so much that, after listening to the audiobook, I even bought a paper copy to have for a reference. I plan to continue to read about AI engineering, but given that I haven't taken formal coursework in the topic, this book served as an equivalent to a graduate school class to give me confidence to dive deeper. Although some math were presented, the audiobook was incredibly accessible, unlike with some technical books. For those who spend time commuting in cars, I recommend listening to the text if you don't have time to flip through a paper book. Overall, this book raised my game significantly about AI. Where other books obscure with technical jargon, this book enlightens with clear concepts. I still need to brush up on a few focused topics to ready myself for a project, but I'm much more fluent about the ideas than before. I highly recommend this in-depth introduction, at least for the next few years until the field outpaces our knowledge once again.

A great resource for anyone looking to enter the field of AI engineering. The book assumes some prior experience with basic ML and AI concepts, which allows it to dive deeper into practical and relevant topics without spending too much time on fundamentals. Highly recommended if you have that foundation and want to take the next step.

The best book on AI Engineering. I enjoyed reading every page of this book. The book cover the whole breadth of the AI engineering field from the platform to the application itself covering very important topics including evaluation and security among others. The book covers all the different approaches for addressing each issues in the application design including the approaches from research and academia. The author has an amazing writing style that is fun to read and learn from.

Very informative. The audio version could use a little polishing like reading a table is not very conducive to the understanding and should be skipped

Enjoying it so far. I’m on chapter 3 as of right now and I can confidently say it’s very eye opening. I’d recommend it to anyone looking into machine learning or AI engineering.

In academia, there is the concept of a "review article" -- it summarizes and organizes the major research findings into a framework that makes it easy to come up to speed on a topic. Frequently, the review articles themselves end up defining the area, and this is what Chip Huyen manages to achieve in this comprehensive book. The quality of the writing and diagams are uniformly high -- Chip uses simple language to great effect. I think of myself as being somewhat up to date, but I have learned something new every chapter and not just minor details. For example, I had missed the Deep Mind paper pointing to "self-delusion" as the reason for hallucinations. Chip provides a clear explanation and shows an example. This fundamentally affects my intuitive understanding of model errors. Of course, there's a danger with writing a review of a fast moving field. Just today, DeepSeek published an article showing that they can avoid SFT altogether and do just train a model on preferences, alphago-style. If this takes off, Chapter 7 will need a second edition. Strongly recommend this book. It's invaluable for anyone building applications using GenAI models.