Skip to content

The spelled-out intro to language modeling: building makemore

1,322,168 views

About this video

Intro · Hand-picked by a BrighterTube curator · found via Developer-Y/cs-video-courses

Part of his Zero to Hero series: code-first, from-scratch teaching by a founding member of OpenAI and former Tesla AI lead.

Karpathy builds makemore, a character-level bigram language model, introducing PyTorch tensors, sampling and negative log-likelihood loss.

Video by Andrej Karpathy, played through YouTube's embedded player.

Part of Neural Networks: Zero to Hero