Style

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 · 16d ago · simedw.com

Automate your B2B brand going viral, with new media creators

AI · 18d ago · company-app.joinastute.com

AI teammates that you can give real work to

AI · 25d ago · x.ai

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

Make your software self-driving

AI · 30d ago · coldtea.ai

Approval-first Agent OS for solo founders

AI · 30d ago · soloop.io

Docs, wikis, tasks – a minimal & unified workspace for teams

Work · 2016 · notion.so

Life & fun · 2016 · mewo2.com

Curated directory of the best pricing pages

Work · 2016 · pages.xyz

Responsive HTML email templates for startups & developers

Growth · 2016 · htmlemail.io

One-to-one video calling. Google's FaceTime competitor.

Work · 2016 · accounts.google.com

Write perfect emails with Artificial Intelligence

AI · 2016 · boomeranggmail.com