Recommends Build a Large Language Model From Scratch.

Transcript context

…It’s available for preorder, and there’s a full digital preprint. I’m just making it pretty and better organized for the physical thing, which is a lot of why I do it—it’s fun to create things that you think are excellent in physical form when so much of our life is digital. I should say, going to Perplexity here, Sebastian Raschka is a machine learning researcher and author known for several influential books. A couple that I wanted to mention—and a book I highly recommend—is Build a Large Language Model From Scratch, and the new one, Build a Reasoning Model From Scratch. I’m really excited about that. Building stuff from scratch is one of the most powerful ways of learning. Honestly, building an LLM from scratch is a lot of fun and a lot to learn. Like you said, it’s probably the best way to learn how something really works, because you can look at figures, but figures can have mistakes. You can look at conceptual explanations, but you might misunderstand them. But if there is code and the code works, you know it’s correct. There’s no misunderstanding; it’s precise. Otherwise, it wouldn’t work. I think that’s the beauty behind coding. It doesn’t lie. It’s math, basically. Even with math, you can have mistakes in a book you would never notice because you aren’t running the math while reading, so you can’t verify it. And with code, what’s nice is you can verify it.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.