Prom.dev
The one night stand of software engineering
What it does
Prom turns prompts into shareable software we call drops. Type an idea, it becomes real, share the link. Done. No commitment, no maintenance, no "where is this going" talk. Just software that exists because you had an idea at 1am. But Prom isn't just a builder. It's a creative platform where you discover and remix what other people are making. Browse trending drops, fork something cool, make it your own. Software is becoming content and Prom is where you make it.
Does the same job
all alternatives →
- PDProm.dev – Prompts that simulate Hacker News (and a tool to share them)Nov 2025 · prom.dev · ▲14
We’re Heather and Matt, and we want to invite you to Prom. Prom is a simple place to share the prompts you’re proud of and discover ones other people actually use. The idea came out of a lightweight internal library we hacked together for our team earlier this year. Before that, we had “good prompts” on Slack or Google Docs. We wanted a dedicated place for prompts, and somewhere people can post what’s working for them, compare approaches and models, and see what “good” looks like in the wild. The tech is, well, nothing fancy, but intentionally lightweight. Flask backend, Bootstrap frontend.…
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
