LLM

I’ve been on the lookout for the rare LLM technology books that go into implementation depth, which is why I was thrilled when Sebastian Raschka’s book Build a Large Language Model (From Scratch) came out. I just learned about another from Sean Carroll’s Mindscape Podcast. Anil Ananthaswamy’s book Why Machines Learn: The Elegant Math Behind Modern AI looks like another good one. Unlike Raschka’s book, this one starts at the dawn of AI history and covers machine learning in depth before discussing LLMs and is focused on the math but not the code.

It’s been interesting to see how LLMs, specifically Claude and ChatGPT, mostly running inside VS Code, do when I built this website. It required knowledge of Hugo, the Hugo framework (Beautiful Hugo) I chose, the Go template language, Markdown, and CSS. From this list, I only had prior experience with Markdown. The LLMs performed shockingly well across all of these languages, looking at the big picture of my code base while doing so. They almost always found solutions to my questions and code changes that I expressed in English. In a few cases, they did not look at a high enough level to see that some things were framework design decisions made years ago while the Hugo platform and best practices marched forward since then.