Ask My Book
Hey HN! I’ve spent the past couple weekends building Ask My Book. You can use Ask My Book to ask a question and get an answer in my voice. It's an experiment in using AI to make my book’s content more accessible. Instead of reading 52,000 words, you can ask a question and get a sub 100-word answer. I'd prefer people read my book! But not everyone has the time... Give it a shot, and let me know what you think. APIs used: GPT-3 (+ embeddings), and Resemble for the voice.
In plain words
Ask My Book is an AI-powered tool that answers questions about a book's content in the author's voice. Users can ask questions and receive concise answers under 100 words, making the book's 52,000 words more accessible without requiring a full read. The tool uses GPT-3 with embeddings to understand queries and Resemble for voice synthesis. It's designed for readers who want specific information from the book but lack time for cover-to-cover reading.
written from the facts on this page · September 2026
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 · 26d ago · cactuscompute.com
Launched alongside, November 2022
the whole month →
- TC
I made a thing! In 2014, I was holding a stack of iPhones and thought to myself: "Hey, if I had each phone display a playing card, I could click a button and they'd shuffle themselves" I pared that idea all the way down to this: trading cards made of e-ink displays. Right now, each card costs me about $20 each, but with only a bit more scale, I think I can get that down to $10. In doing this project, I learned how to design electronics and circuit boards. I learned Rust and wrote my first driver, I upped my CAD skills, 3D printed, and did my first resin casting. I generated the images on the…
Dev tools · 2022 · wyldcard.io
