This is your work, valued

AI researcher and educator building minimal, interpretable implementations of large language models and training systems.

LLM training and inference optimizationEducational implementations from first principlesMulti-agent LLM reasoning and collaborationLow-level systems and C/CUDA implementationsLLM-assisted research and knowledge toolsTokenization and BPE algorithms

inferred from the public footprint

Wed
Thu
Fri
Sat
Sun
Mon
Yesterday
Active 26d ago
Stanford

Andrej

Top 11%
@karpathy

He ships focused implementations of large language models and reasoning systems: nanoGPT distills training down to essentials, nanochat proves you don't need massive infrastructure to get capable results, and llm-council explores how multiple models collaborate. Nearly 480k GitHub stars across his projects.

Nanochat. I built a way to train your own ChatGPT for fifty dollars.

57k

Autoresearch. I built an AI that experiments on machine learning models while you sleep.

92k

Council. I built a tool that asks multiple AI models to answer your questions and debate the best response.

23k

NanoGPT. I made the simplest code to train your own AI language model.

62k

LLM101n. I built a course that teaches you to create an AI storyteller from scratch.

38k

LLM.C. I built AI model training that runs in plain C without bloated dependencies.

31k

Reader3. I made a simple ebook reader that works with AI models to read books together.

3.8k

Job Market Visualizer. I built an interactive map of every US job with government data.

1.9k

Rendergit. I built a tool that flattens GitHub repos into searchable single pages.

2.4k

Karpathy's Blog. I write a blog explaining AI and machine learning concepts clearly.

1.8k

Neural Networks Zero to Hero. I made a course teaching neural networks from the ground up.

24k

HN Time Capsule. I built a tool that grades decade-old predictions with hindsight.

667

Rustbpe. I made a fast, simple tool for training AI tokenizers.

502

Llama2.c. I made an AI model you can train and run in one C file.

20k

MinBPE. I wrote clean code for the text-splitting algorithm all AI models use.

11k

Build NanoGPT. I made a video course teaching how to build GPT-2 from scratch.

5.4k

MinGPT. I built GPT from scratch in 300 lines of readable code.

25k

NanoGPT Lecture. I published the code from my neural networks video course so people can learn by building.

4.9k

Makemore. I made a tool that generates realistic new text by learning from examples.

4.1k

Calorie. I made a simple calorie deficit tracker for weight loss.

160

Random Fun. I collected my experimental notebooks and scripts in one place.

1.2k

Karpathy. I shared my thoughts and experiments on how AI models work.

173

Arxiv Sanity. I built a website that tames the overwhelming flood of research papers.

5.7k

Arxiv Sanity. I made a tool that learns which research papers interest you and recommends similar ones.

1.7k

Cryptos. I built Bitcoin from scratch in Python to show how it works.

1.9k

Micrograd. I built a tiny AI learning engine you can read in an afternoon.

17k

LeCun 1989 Repro. I reproduced Yann LeCun's 1989 handwritten digit recognition experiment.

776

Deep Vector Quantization. I wrote training code for turning images into learnable symbol sequences.

654

SVM.js. I built a machine learning sorter that runs in the browser.

709

NeuralTalk2. I built software that automatically writes captions for images.

5.6k

tsneJS. I wrote a tool that visualizes large datasets as interactive maps.

912

Paper Preview. I made scripts that turn research papers into browsable web pages.

186

EigenLibSVM. I built a C++ tool for training machine learning models on matrix data.

109

Ulogme. I built software that tracks your computer activity and shows you a timeline of your day.

1.2k

Agent Trainer. I wrote reinforcement learning agents for simulated environments.

146

Forest. I built a random forest tool for MATLAB with pluggable learners.

227

NeuralTalk. I built an AI that describes images with sentences.

5.5k

CharRNN. I built an AI that learns to write by studying text samples.

12k

Gitstats. I built a tool that shows your team's recent work across all code branches.

146

ScholarOctopus. I made a map of 7000 academic papers from major conferences.

88

REINFORCEjs. I built a learning system where programs improve through trial and error.

1.5k

Density Estimator. I implemented a density estimation model in about 150 lines of code.

594

RecurrentJS. I built AI models with memory in the browser.

985

ResearchLei. I made a filing system for research papers you can actually search.

276

Covid Sanity. I built a searchable library of COVID-19 research papers organized by similarity.

393

ForestJS. I made a machine learning tool that learns patterns and makes predictions in JavaScript.

339

NotPygameJS. I made a toolbox for building games in web browsers.

109

Research Pooler. I built a tool that automatically finds related research papers for you.

492

Find Birds. I built a tool that finds Twitter accounts you should follow.

370

Normalizing Flows. I built an educational tool for understanding how normalizing flows transform data.

917