A social media network where users share prompts instead of posts
Social media these days feels like swimming through a feed of AI generated slop rather than actual human thoughts. Sometimes I wonder what the prompts behind the posts are. I bet there's more creativity going into the prompts than the final content that actually gets shared. What if people just shared their prompts, and the completion was rendered on-demand, client side? Disclaimer: This is a vibe coded proof-of-concept, not a functional service, built in the no-code builder Mocha. It's seeded with a few fake posts. You can create your own posts but they're just saved locally on your own…
In plain words
This is a proof-of-concept social network where users share AI prompts instead of finished posts, with completions generated on-demand in the browser. Built as a no-code prototype in Mocha, it explores the idea that prompt crafting contains more creativity than AI-generated content itself. Users can create and view prompts seeded with examples, though posts save only locally and require an OpenAI API key to generate completions using the inexpensive 4o-mini model. It is not yet a functional service.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Social media these days feels like swimming through a feed of AI generated slop rather than actual human thoughts. Sometimes I wonder what the prompts behind the posts are. I bet there's more creativity going into the prompts than the final content that actually gets shared. What if people just shared their prompts, and the completion was rendered on-demand, client side? Disclaimer: This is a vibe coded proof-of-concept, not a functional service, built in the no-code builder Mocha. It's seeded with a few fake posts. You can create your own posts but they're just saved locally on your own device. To run the completions, you'll need to drop in an OpenAI API key. It uses 4o-mini, so the API calls are super cheap.
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, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
