Friday, April 18, 2025

How LLMs Work, by Andrej Karpathy

Andrej Karpathy, Eureka Labs founder and computer scientist (Tesla, OpenAI), explains how language models work, and are built. You'll need about 3.5 hours to view the whole video, but it covers transformer networks, training (human and algorithmic; labeling) and reinforcement learning. 

No comments:

Cutting Opex to Support AI Capex Probably Sets Stage for More of the Same

In a brutal way, the notion that the business value of artificial intelligence hinges in large part on displacing human labor has already be...