Andrej Karpathy

Stable diffusion dreams of steam punk neural networks

[1hr Talk] Intro to Large Language Models

The spelled-out intro to language modeling: building makemore

Building makemore Part 5: Building a WaveNet

The spelled-out intro to neural networks and backpropagation: building micrograd

Let's reproduce GPT-2 (124M)

Let's build GPT: from scratch, in code, spelled out.

Stable diffusion dreams of psychedelic faces

Stable diffusion dreams of steampunk brains

Stable diffusion dreams of "blueberry spaghetti" for one night

Building makemore Part 4: Becoming a Backprop Ninja

Stable diffusion dreams of steam punk neural networks

Building makemore Part 2: MLP

How I use LLMs

Let's build the GPT Tokenizer

Building makemore Part 3: Activations & Gradients, BatchNorm

Stable diffusion dreams of tattoos