Yet here we are

Can we get a dedicated 4090 owners group for ai models that work on it?

What an interesting funding strategy for a Claude sub

Use ai to build it a poc and read the code after, learn, rebuild until you find something that works.

I host all of my custom applications on a machine in my home with Tailscale, k8, infrastructure as code

It’s wired, always on, has access to my gpu running on another machine or falls back to cloud inference

Self hosted GitHub action runners on each different platform for build/deploy of various projects: tauri v2, apis, web uis, native macOS apps, Unity 3d

None of this existed a month ago and it’s been a blast pretending to run my own platform

Obviously

You already can, very easily

I put on my pm hat and queue up work

An agent spawns, coordinates, reviews sub agents

It works for hours and if you have good fundamentals, is extremely accurate