Skip to content

State of GPT | BRK216HFS

786,019 views

About this video

Hand-picked by a BrighterTube curator · found via HackerTube (Karpathy's dataset of videos Hacker News recommends

Andrej Karpathy walks through how GPT assistants are trained, from pretraining and tokenisation to supervised fine-tuning and RLHF, then gives practical prompting advice grounded in how models think; dense and clear from one of the field's best teachers.

Andrej Karpathy explains how GPT assistants are trained (pretraining, fine-tuning, RLHF) and how to use them well.

Video by Microsoft Developer, played through YouTube's embedded player.

Part of Neural Networks: Zero to Hero