All books recommended on Ask HN
After reading this Ask HN post [1] (and buying too many books), I found myself going through old posts about book recommendations. I wanted to find all books recommended in those posts and save the top ones for future book shopping sprees. This has been done before [2, 3], but I wanted to get books that were recommended, not just mentioned. I used the Algolia API [4] to get all Ask HN posts about books, reviewed them and filtered out ones that were too specific e.g best books to learn math. The comments were then sent to the Open AI API [5] to extract books that are recommended. I then…
In plain words
All Books Recommended on Ask HN aggregates book recommendations from Hacker News discussion threads. The tool uses the Algolia API to identify Ask HN posts about books, then applies AI to extract which titles were actually recommended rather than merely mentioned. It filters out overly specific posts and consolidates recommendations that refer to the same book under different names or spellings. Users can browse suggestions organized by original posts and view statistics about which recommenders appear most frequently. The result is a curated database designed to help readers discover books that have been genuinely endorsed by the Hacker News community.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
After reading this Ask HN post [1] (and buying too many books), I found myself going through old posts about book recommendations. I wanted to find all books recommended in those posts and save the top ones for future book shopping sprees. This has been done before [2, 3], but I wanted to get books that were recommended, not just mentioned. I used the Algolia API [4] to get all Ask HN posts about books, reviewed them and filtered out ones that were too specific e.g best books to learn math. The comments were then sent to the Open AI API [5] to extract books that are recommended. I then grouped them, but books can be mentioned with different names (Godel, Gödel, GEB?), and GPT4 wasn't doing a good job finding similar titles in a long list (25k titles). So that part had to be done mostly manually. Finally, I added a page to browse by posts, some stats (like users who recommended the most books), and highlighted mentioned books in the comments. I hope you find a good book! Feedback is welcome :) [1] https://news.ycombinator.com/item?id=41756432 [2] https://hacker-recommended-books.vercel.app [3] https://ramiro.org/vis/hn-most-linked-books/ [4] https://hn.algolia.com/api [5] https://platform.openai.com/docs/api-reference/introduction
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, October 2024
the whole month →
Softr for Notion▲925Turn Notion databases into portals & apps with no code
Dev tools · 2024 · softr.io
One inbox for all your work discussions
Work · 2024 · generalcollaboration.com