# karpathy/jobs

A research tool for visually exploring Bureau of Labor Statistics Occupational Outlook Handbook data. This is not a report, a paper, or a serious economic publication — it is a development tool for exploring BLS data visually.

Repository: https://github.com/karpathy/jobs
Canonical: https://ross.abutalabs.com/products/jobs
Language: HTML
License Family: other
Last push: 2026-03-16T04:05:24+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 72, release rhythm 35, longevity 12
- inputs: {"age_days": 172, "days_push": 170, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1989, forks 375 (observed 2026-08-28T04:06:02.878474+00:00)

## What it is
A research tool that scrapes the Bureau of Labor Statistics Occupational Outlook Handbook (342 occupations) and renders an interactive treemap where rectangle area is employment and color encodes metrics like pay, growth outlook, education, and LLM-scored AI exposure. It includes a full Python pipeline (scrape, parse, tabulate, LLM-score, build site data) plus an HTML/JS frontend.

## Use cases
- visually explore US labor market data by occupation
- see which jobs have high AI exposure
- compare median pay and education requirements across occupations
- run custom LLM prompts to score occupations on any criteria
- scrape and parse BLS Occupational Outlook Handbook pages into structured data
- build a treemap visualization from employment statistics

## When to choose
- you want an interactive visual overview of BLS occupation data
- you want to experiment with LLM-based scoring of occupations using custom prompts
- you need a ready-made scraping and parsing pipeline for the BLS OOH
- you want a starting point for exploring labor-market questions like automation or offshoring risk

## When to avoid
- you need rigorous, peer-reviewed economic analysis or predictions
- you need a maintained product with a license or support guarantees
- you need non-US labor data or sources other than the BLS OOH
- you need production-grade data pipelines with error handling and scheduling

## Facets
- artifact type: application
- maturity: active
- function: data-visualization, web-scraping, parser, llm-inference, etl, charts
- domain: data-visualization, data-science, analytics, large-language-models, developer-tools, education
- platform: python, browser, cross-platform
- tags: treemap, bls-data, labor-statistics, occupations, ai-exposure, scraping-pipeline, llm-scoring, interactive-visualization, web

## Member repositories
- karpathy/jobs (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:02.878474+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 2026-08-30T03:02:49.498798+00:00, confidence not recorded.
  - readme: https://github.com/karpathy/jobs (fetched 2026-08-28T04:06:02.878474+00:00, sha 7736f4e45162)
- Data as of 2026-08-30T08:39:29.467469+00:00.