← Back to Directory
Andrej Karpathy

Andrej Karpathy

Builder

San Francisco

@karpathy

Building Eureka Labs — AI-native education. Created nanoGPT and built neural networks from scratch on YouTube. Previously Director of AI at Tesla, founding member of OpenAI.

Skills

deep learningcomputer visionLLMseducationpython

Looking For

collaborator

Research Foundations (2)

Attention Is All You Need

NeurIPS 201720176,510 citations

Used by: nanoGPT

Language Models are Few-Shot Learners

NeurIPS 202020203,027 citations

Used by: nanoGPT

Projects (1)

nanoGPT

GitHub

The simplest, fastest repository for training/finetuning medium-sized GPTs. Reproduces GPT-2 (124M) in ~$20 of compute.

NLPGenerative AI

Built on research:

paperAttention Is All You Need(2017)
paperLanguage Models are Few-Shot Learners(2020)

AI Suggested Researchers

Researchers whose work may be relevant to your projects (auto-detected)

Kyunghyun Cho

Kyunghyun Cho

New York University / Genentech

Shared domains: NLP, Generative AI
63% matchAI suggested
Aaron Courville

Aaron Courville

Mila / Université de Montréal

Shared domains: NLP, Generative AI
63% matchAI suggested
Luke Zettlemoyer

Luke Zettlemoyer

University of Washington / Meta AI

Shared domains: NLP, Generative AI
62% matchAI suggested
Hannaneh Hajishirzi

Hannaneh Hajishirzi

University of Washington / Allen AI

Shared domains: NLP, Generative AI
61% matchAI suggested

AI Suggested Papers

Papers that may have inspired your projects (auto-detected by domain & keyword analysis)

WebsiteTwitterGitHub