This week on the show, Scott talks to Philip Kiley about his new book, Inference Engineering. Inference Engineering is your guide to becoming an expert in inference. It contains everything that Philip has learned in four years of working at Baseten. This book is based on the hundreds of thousands of words of documentation, blogs, and talks he's written on inference; interviews with dozens of experts from our engineering team; and countless conversations with customers and builders around the world.
00:00 Did you feel uncomfortable that you don't have a PhD in machine learning and deep learning?
01:03 Introduction to Philip Kiley and 'Inference Engineering'
02:09 Was that a conscious decision to do something like that?
07:11 Purpose and Audience of 'Inference Engineering'
14:37 Do you think about what can be done with AI, considering it can't currently write a good book on AI inference?
17:23 How much faster can AI performance get, and will it result in less energy consumption and lower costs?
24:14 AI Proofreading and Human Collaboration
31:28 Why is it difficult to get paper copies of the book listed on Amazon despite high demand?
