Andrej Karpathy on llm.c CUDA Keynote | Generated by AI

Home 2026.01

Question: What does the YouTube video at https://www.youtube.com/watch?v=aR6CzM0x-g0 say?

Answer:

The video is a keynote talk titled **“CUDA Mode Keynote Andrej Karpathy Eureka Labs”** by Andrej Karpathy, presented at the first CUDA Mode IRL hackathon event organized by Accel.

In it, Karpathy explains the creation and details of his project llm.c — a from-scratch implementation to train language models (specifically recreating GPT-2 style training) purely in C/CUDA, with almost no external dependencies (except optionally cuBLAS for FlashAttention).

Main points he covers:

He also mentions community contributions that helped optimize the code, challenges learning modern CUDA (outdated resources), and future plans like adding Llama 3.1 support and FP8.

The talk is technical but accessible if you’re familiar with deep learning basics; it’s in English, roughly 45–60 minutes long, and includes slides with code snippets.

Karpathy also wrote a detailed accompanying Twitter/X thread breaking it down further.

References:


Back

x-ai/grok-4.1-fast

Donate