Machine Learning
I’ve completed changing my code to support a model designed to win games rather than guess legal moves. The model is the same, but the reward function, some game details, and much of the administrative framework has changed. The actual…
Machine Learning
I started actually doing AI again. As I was watching all the Karpathy videos, I found myself wanting to stop watching videos and get back to building. I could have gone out and built Karpathy’s nano-gpt model, but he already…
Machine Learning
In my last post, I discussed how Andrej Karpathy fell a little short on building intuition around the attention mechanism in his Neural Nets – Zero to Hero series. In that post I shared how I was doing my own diagrams of…
Machine Learning
I’ve been going through Andrej Karpathy’s Neural Nets: Zero to Hero playlist. I’ve spent the last few days on one of the later ones: Let’s build GPT: from scratch, in code, spelled out. As an aside, I should note that…
Machine Learning
What a difference a great teacher makes. Recently, I completed the Coursera Generative AI with Large Language Models course. As I alluded to on LinkedIn, it was a letdown. It didn’t explain the mechanics of how LLMs work. The closest…