Ask anything from Paul Graham powered by GPT-3
As a programmer and entrepreneur, Paul Graham's essays have inspired many in the tech community. I grew up reading his essays frequently. Previously, I would use Google and perform a site search with keywords to find Paul Graham's thoughts on a topic. With the launch of GPT-3 and vector search capabilities, I have created an app that makes it easier to find specific insights and perspectives from Paul Graham's essays. The app indexes and categorizes each essay, providing a streamlined way for users to access and understand Graham's thoughts on programming, startups, and innovation. Do try it…
In plain words
This app allows programmers and entrepreneurs to search Paul Graham's essays using AI-powered vector search and GPT-3. Users can query Graham's thoughts on topics like programming, startups, and innovation without manually browsing his site. The app indexes and categorizes his essays to surface relevant insights and perspectives quickly. It's designed for those who regularly reference Graham's work but want a faster way to find specific ideas and advice.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
As a programmer and entrepreneur, Paul Graham's essays have inspired many in the tech community. I grew up reading his essays frequently. Previously, I would use Google and perform a site search with keywords to find Paul Graham's thoughts on a topic. With the launch of GPT-3 and vector search capabilities, I have created an app that makes it easier to find specific insights and perspectives from Paul Graham's essays. The app indexes and categorizes each essay, providing a streamlined way for users to access and understand Graham's thoughts on programming, startups, and innovation. Do try it out and let me know your feedback in the comments.
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
