Summary
A Show HN post introduces HackerBooks, a site that lists roughly 16,500 books that at least two different Hacker News commenters have mentioned since 2007. Each book links back to the comments that mentioned it, and the underlying data can be downloaded from the site's about page. The author says it was inspired by Karpathy's HackerTube and that Claude, specifically Opus 5.5, built almost all of it, including the data pipeline and the site, while the author mainly steered and made decisions. The source snippet is cut off, so details beyond these points are not confirmed.
AI-assisted summary based on the listed source.
What happened
Saw Karpathy's HackerTube and wanted the same thing for books. So I had Claude build one (Opus 5.5). It's ~16.5k books that at least two different HN commenters brought up, from 2007 till now. Each book links back to the comments that mentioned it. Data is downloadable from the about page. To be clear: Claude...
Why it matters
The project is a concrete example of an AI model writing most of a working data pipeline and website from a simple brief, which may interest developers evaluating how much of a small project AI can handle. Readers who want book recommendations drawn from community discussion can use the comment links to check context. Watch whether the downloadable dataset is used by others and how the author describes the division of work as the project develops.
Signal Intelligence
Signal Strength 88%
Technical label WATCH
Public Interest 35
Category BIG MOVE
Reader Depth PRACTICAL
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
Recognizable Entity Score 51
Practical Impact Score 0
Novelty Interest Score 70
Consequence Score 18
Curiosity Score 0
Shareability Score 52
Why this is here
VQV surfaced this signal because it is recent, relevant to Consumer AI, connected to Hacker News Front Page.
