HackerTube: YouTube built from videos recommended by HN
Summary
Andrej Karpathy used Claude Opus 5.5 to build HackerTube (hackertube.org), a YouTube-style site featuring 6,454 videos recommended across 40K Hacker News comments from 2007-2026, developed end-to-end in about two hours.
View Cached Full Text
Cached at: 10/31/26, 09:21 PM
Similar Articles
@FinanceYF5: Someone rebuilt a better YouTube in 2 hours 1/ YouTube’s recommendations weren’t good enough, so Karpathy simply rebuilt it himself. He had Claude analyze 43 million comments from the past 20 years of Hacker News and identify the repeatedly recommended 6,4…
Karpathy used Claude to analyze 43 million Hacker News comments from the past 20 years, identify 6,454 repeatedly recommended videos, and rebuild HackerTube into a better YouTube recommendation tool in about 2 hours.
Show HN: Wikihack – HackerTube, but for Wikipedia articles mentioned on HN
Wikihack is a frontend-only web tool that scrapes Wikipedia mentions from Hacker News and presents them in a scrollable feed with Top, Random, and Rising rankings, inspired by Karpathy's HackerTube and Hackerbooks.
Show HN: HackerBooks – HackerTube, but for books mentioned on HN
Show HN: HackerBooks, a web tool that surfaces books mentioned in Hacker News comments, with keyboard navigation and trending/rising lists.
@_sholtodouglas: - Claude fighting for you. Short form video and rec sys attractor basins are the cigs of our generation. Your time can …
A discussion criticizing the addictive 'attractor basins' of short-form video and recommendation feeds, highlighting Andrej Karpathy's weekend project HackerTube, which used Claude to filter 43M Hacker News comments down to 6,454 highly-recommended YouTube videos for a much better viewing experience.
@omarsar0: Introducing Hacker Papers! I absolutely love this HackerTube idea from @karpathy. So I took his prompt and similar data…
DAIR.AI's Omar (@omarsar0) built 'Hacker Papers', an agent-generated collection of 1K+ arXiv papers mapped to their Hacker News discussion threads, inspired by Andrej Karpathy's HackerTube idea. The tool lets readers explore popular papers alongside community engagement stats over time.