Andrej Karpathy
BuilderSan 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
Looking For
Projects (1)
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs. Reproduces GPT-2 (124M) in ~$20 of compute.
Built on research:
AI Suggested Researchers
Researchers whose work may be relevant to your projects (auto-detected)
Yann LeCun
Meta AI / NYU
Geoffrey Hinton
University of Toronto
Demis Hassabis
Google DeepMind
Yoshua Bengio
Mila / Université de Montréal
AI Suggested Papers
Papers that may have inspired your projects (auto-detected by domain & keyword analysis)
For nanoGPT:
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
NeurIPS 2022 · 2022 · 5,200 citations
Training language models to follow instructions with human feedback
NeurIPS 2022 · 2022 · 8,500 citations
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
ICLR 2019 · 2019 · 6,500 citations