Understanding how to write good prompts (prompt engineering) is still very much a relevant skill if you want to effectively use LLMs. Harnesses aren't magic.
This post describes ideas found in existing agent orchestrator systems since they've existed. You'll find the same "top level agent that breaks a problem down into spec / plan / implement / verify" pattern in get-shit-done or superpowers.
Is the original part the VCS that works at 1000 commits/second? Or spending a bunch of money comparing models?
Eyebrows will raise at Anthropic / OpenAI, perhaps. Why are they charging 1000x more for the exact same business?
The 'distillation is theft!' shtick won't last long. In fact, unlike Anthropic/OpenAI, these Chinese labs actually had to pay for that 'stolen' training data.
email: dymk (at) dymk (dot) co
woodworking: https://www.longtailwoodcraft.com/gallery.html