03 Andrej Karpathy Open source

Karpathy's HackerTube: 6,454 videos picked from 43M HN comments, with the data released

Concept illustration (generated)

What is it?

HackerTube collects the YouTube videos that Hacker News commenters have kept recommending to each other for 20 years. Karpathy had Claude filter 43 million HN comments Vendor claim down to 6,454 videos Vendor claim, and says he built it in about two hours with Claude Code on Opus 5.5 at Medium effort. There's no login; state stays in your browser session, and thumbnails are a frame from the middle of the video. The comment analysis is downloadable as a single zip.

Why does it matter?

The point is the data: Karpathy invites you to point your own coding agent at the zip and build your own version. It's a compact example, from raw data to deployment, of using an LLM to filter a huge text corpus into a curation product, which maps well onto internal knowledge curation. Karpathy says his only manual steps were creating an API key, starting a VPS and buying the domain, a useful gauge of how much you can hand an agent.

Maturity

BetaRated beta: it's open to everyone but it's a personal weekend project. The source code isn't published yet; only the data zip is.

How to track it

  • Code release: watch Karpathy's GitHub for a HackerTube repository.
  • Data reuse: look for spin-off sites and analyses built from the zip on X and HN.

More from the same day