I mapped HN's favorite books with GPT-4o
Hey HN! I love finding new books to read on here. I wanted to gather the most mentioned books and recreate the serendipity of physical browsing. I scraped 20k comments from HN threads related to reading, extracted the references and opinions using GPT-4o mini, and visualised their embeddings as a map. - OpenAI's embeddings were processed using UMAP and HDBSCAN. A direct 2D projection from the text embeddings didn't yield visually interesting results. Instead, HDBSCAN is first applied on a high-dimensional projection. Those clusters tend to correspond to different genres. The genre…
I mapped HN's favorite books with GPT-4o launched on September 7, 2024 with 285 votes, #168 of 5,281 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 2 years on.
In plain words
This tool creates an interactive map of books frequently mentioned in Hacker News discussions about reading. It scraped 20,000 comments from reading-related threads, extracted book references using GPT-4o mini, and visualized them as a browseable map organized by genre. The interface mimics the experience of physical book browsing, allowing users to explore interconnected books and their community-sourced descriptions. Books are clustered and spatially arranged to reveal thematic relationships across genres.
written from the facts on this page · September 2026
From the sources
The 1000 most popular books on Hacker News visualized on an interactive map.
Map data could not be loaded. Please reload or browse the book list . This is a map of the 1000 most mentioned books on Hacker News . You can also see it as a list . I scraped 20k posts related to books and reading from Algolia . I used GPT-4o to parse the posts and extract references to books, along with the opinions of the posters. These were collated into descriptions, which were then embedded using OpenAI's model. The embeddings were projected into 2D using PaCMAP and clustered with HDBSCAN . Cluster labels were generated with GPT as well. The clusters were packed as circles to get an aesthetically pleasing result. The corresponding covers were aligned on a staggered grid, stitched…from hnbooks.pieterma.es
In the maker’s words, at launch
Hey HN! I love finding new books to read on here. I wanted to gather the most mentioned books and recreate the serendipity of physical browsing. I scraped 20k comments from HN threads related to reading, extracted the references and opinions using GPT-4o mini, and visualised their embeddings as a map. - OpenAI's…
Does a similar job
all alternatives →
40k HN comments mentioning books, extracted using deep learning2021 · hacker-recommended-books.vercel.app · ▲1,359Thinking, Fast and Slow - with 523 comments from the Hacker News community
Exploring HN by mapping and analyzing 40M posts and comments for fun2024 · blog.wilsonl.in · ▲520Accessible end-to-end deep dive of crawling, embedding, projecting, and semantic searching all of Hacker News for my Hackerverse project.
- HAHackYourNews – AI summaries of the top HN stories2023 · hackyournews.com · ▲335
Hey there HN! I wanted to share a pet project of mine. I built HackYourNews [1] to scratch a personal itch: Knowing which stories to focus on while browsing aimlessly (though there is a certain joy in that, as well!) HackYourNews uses OpenAI's gpt-3.5-turbo to summarize the destination article as well as the comments section. Summarization of the article is always cached, while summaries of the comments are regenerated if the comments count is >10% (or >10 comments) different. While I styled the homepage to welcome HNers, my preferred view is the Mobile view, accessed from the navbar. This…
- ISI scraped 3B Goodreads reviews to train a better recommendation modelNov 2025 · book.sv · ▲606
Hi everyone, For the past couple months I've been working on a website with two main features: - https://book.sv - put in a list of books and get recommendations on what to read next from a model trained on over a billion reviews - https://book.sv/intersect - put in a list of books and find the users on Goodreads who have read them all (if you don't want to be included in these results, you can opt-out here: https://book.sv/remove-my-data) Technical info available here: https://book.sv/how-it-works Note 1: If you only provide one or two…
Building a web search engine from scratch with 3B neural embeddings2025 · blog.wilsonl.in · ▲699End-to-end deep dive of the project, spanning a large GPU cluster, distributed RocksDB, and terabytes of sharded HNSW.
- TBTop books mentioned in comments on Hacker News2016 · hackernewsbooks.com · ▲463
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, September 2024
the whole month →
BeforeSunset AI 2.0▲1,267Personalized AI daily planning that suits your life
AI · 2024 · beforesunset.ai
