←News detail

indigoUpdated Nov 2 11:30

Karpathy built HackerTube with Claude, filtering 6,454 recommended videos from 43 million HN comments

AI summary

Andrej Karpathy built the weekend project HackerTube with Claude Code and Opus 5.5, filtering 6,454 consistently recommended videos from 43 million comments across 20 years of HN, taking about 2 hours. The site requires no login, keeps state in the local browser session, and uses a representative frame from the middle of each video as the thumbnail. He said that aside from applying for a Google Cloud API key, setting up a VPS, and buying a domain, all other updates, hardening, deployment, and optimization were left to Claude, and the comment analysis data was packaged into a zip file so Claude could use it to generate its own version.

Why read this

AI score 62

Karpathy built a personalized video recommendation site with Claude Code in two hours, demonstrating a viable path for letting an Agent complete development and deployment end to end.

Topics

Tags

Quoted post

Andrej Karpathy

@karpathy

Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5: https://t.co/JIhXN7OSh1 - Excellent recs without any logins (state is kept in local browser session) - Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads - Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version - HackerTube Longs ✊ A bit more on the process: I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing. Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.

View original

Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5: https://t.co/JIhXN7OSh1 - Excellent recs without any logins (state is kept in local browser session) - Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads - Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version - HackerTube Longs ✊ A bit more on the process: I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing. Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.

View original post

Body · AI translation

Truly personalized recommendations! Andrej's weekend project: HackerTube. He had Claude sift through 43 million HN comments from the past 20 years to surface 6,454 consistently recommended videos. It significantly improved the viewing experience, and with Opus 5.5 it took about 2 hours! I'm sure everyone has long suffered from YouTube's recommendations—from now on, we should all let our own Agents help recommend content 👀

Source

indigo