Comment by russellbeattie

I've been working on a custom orchestration system which starts by creating an overall work plan, then splitting up development tasks among agent/model combos depending on their capabilities/expense, then coordinating their output, testing, etc. with various adversarial agents acting as gates throughout the process. It's really satisfying to watch the task board as agents go through their little routines.

It's been an absolutely fantastic way to set tokens on fire and watch them burn, and produce pretty much nothing of value.