# HackerTube

Published articles for HackerTube.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## How I Built an AI-Powered Hacker News Book Recommendation Site in 2.5 Hours

DevFeed: [How I Built an AI-Powered Hacker News Book Recommendation Site in 2.5 Hours](<https://devfeed.tech/articles/how-i-built-an-ai-powered-hacker-news-book-recommendation-site-in-2-5-hours-116237.md>)

Original publisher: [Read original article](<https://hackernoon.com/how-i-built-an-ai-powered-hacker-news-book-recommendation-site-in-25-hours?source=rss>)

Author: Ishank Choudhary

Published: 2026-11-04T08:53:43Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [GitHub Pages](<https://devfeed.tech/topics/github-pages.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [rate-limiting](<https://devfeed.tech/topics/rate-limiting.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [api](<https://devfeed.tech/tags/api.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [apis](<https://devfeed.tech/tags/apis.md>), [blindsight](<https://devfeed.tech/tags/blindsight.md>), [books](<https://devfeed.tech/tags/books.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-sonnet](<https://devfeed.tech/tags/claude-sonnet.md>), [claude-sonnet-5-5](<https://devfeed.tech/tags/claude-sonnet-5-5.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [hacker-news](<https://devfeed.tech/tags/hacker-news.md>), [hacker-news-books](<https://devfeed.tech/tags/hacker-news-books.md>), [hackertube](<https://devfeed.tech/tags/hackertube.md>), [karpathy](<https://devfeed.tech/tags/karpathy.md>), [llms](<https://devfeed.tech/tags/llms.md>), [programming](<https://devfeed.tech/tags/programming.md>), [time](<https://devfeed.tech/tags/time.md>)

### AI overview

HackerShelf applies HackerTube's crowd-signal method to book recommendations in Hacker News comments. It scanned 9.44 million comments from January 2024 to August 2026, used DuckDB filters to reduce candidates to 11,519, Gemini extraction to identify 6,076 mentions, and Open Library matching plus a three-people/three-month threshold to produce 151 books. The static GitHub Pages site contains 723 mentions from 601 recommenders across nine categories. The build took about 2.5 hours wall-clock, with roughly 40 minutes spent coding in Cursor; most remaining time went to API calls and rate limits. Gemini's free tier cost $0, though the author estimates about $2.15 at listed token rates and does not know Cursor's cost. Limitations included a wrong Open Library match for 1984 and 470 paraphrased quotes that were removed. A spot-check of 10 books and 83 mentions found the authors correct and quotes verbatim.

### Source excerpt

Karpathy built HackerTube in about 2 hours with Claude Code. I rebuilt it for books with Cursor. Here's my honest time, cost, and everything that broke.

## HackerTube

DevFeed: [HackerTube](<https://devfeed.tech/articles/hackertube-112625.md>)

Original publisher: [Read original article](<https://blog.adafruit.com/2026/11/02/hackertube/>)

Author: Ben

Published: 2026-11-02T20:17:51Z

Content type: article

Language: en

Sources: [Adafruit Industries](<https://devfeed.tech/sources/adafruit-industries-makers-hackers-artists-designers-and-engineers.md>)

Topics: [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [browser](<https://devfeed.tech/tags/browser.md>), [claude](<https://devfeed.tech/tags/claude.md>), [clone](<https://devfeed.tech/tags/clone.md>), [content](<https://devfeed.tech/tags/content.md>), [custom](<https://devfeed.tech/tags/custom.md>), [data](<https://devfeed.tech/tags/data.md>), [forum](<https://devfeed.tech/tags/forum.md>), [hacker-news](<https://devfeed.tech/tags/hacker-news.md>), [hackertube](<https://devfeed.tech/tags/hackertube.md>), [local](<https://devfeed.tech/tags/local.md>), [quality](<https://devfeed.tech/tags/quality.md>), [recommendations](<https://devfeed.tech/tags/recommendations.md>), [state](<https://devfeed.tech/tags/state.md>), [thumbnail](<https://devfeed.tech/tags/thumbnail.md>), [uncategorized](<https://devfeed.tech/tags/uncategorized.md>), [user](<https://devfeed.tech/tags/user.md>), [uses](<https://devfeed.tech/tags/uses.md>), [videos](<https://devfeed.tech/tags/videos.md>), [youtube](<https://devfeed.tech/tags/youtube.md>)

### AI overview

HackerTube is a YouTube clone limited to videos suggested on Hacker News, created after Andrej Karpathy expressed frustration with YouTube's algorithm. The text says it uses a custom "ForYou" recommendation system without user accounts, keeps state in the local browser session, offers keyboard shortcuts, uses a "50% thumbnail" instead of uploaded thumbnails, and lets users export site data to help an agent create a version of the site.

### Source excerpt

Frustrated with YouTube's algorithm, Andrej Karpathy asked Claude to whip up HackerTube. HackerTube is a clone of YouTube but only has the videos suggested on the Hacker News forum. HackerTube: Contains quality content Uses the 50% thumbnail instead of the uploaded thumbnail Custom and good ForYou recommendations without any user accounts, storing state in local [...]