# karpathy/randomfun

Notebooks and various random fun

Repository: https://github.com/karpathy/randomfun
Canonical: https://ross.abutalabs.com/products/randomfun
Language: Jupyter Notebook
License Family: other
Last push: 2023-04-18T17:49:08+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4047, "days_push": 1233, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1179, forks 149 (observed 2026-08-28T04:03:53.293153+00:00)

## What it is
A collection of Jupyter notebooks and random scripts by Andrej Karpathy used for experimentation and learning. It serves as a playground of educational machine-learning code rather than a reusable library.

## Use cases
- learn how transformers and language models work from scratch
- find example notebooks explaining ML concepts
- study Karpathy's experimental deep-learning code
- reproduce small educational ML experiments
- get starter notebooks for learning neural networks

## When to choose
- you want readable, educational notebooks on deep learning topics
- you're learning ML and want well-explained example code
- you want to see how Karpathy prototypes ideas

## When to avoid
- you need a production-ready library with an API
- you need maintained, tested software with a license file
- you need stable, versioned releases

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, llm-training, data-science
- domain: machine-learning, deep-learning, large-language-models, tutorials
- platform: python
- tags: jupyter-notebooks, experiments, educational, scratch-code

## Member repositories
- karpathy/randomfun (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:53.293153+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:26:02.915222+00:00, confidence not recorded.
  - readme: https://github.com/karpathy/randomfun (fetched 2026-08-28T04:03:53.293153+00:00, sha 0df9ea2e081b)
- Data as of 2026-08-30T08:39:29.467469+00:00.