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.
The parts outside of the “Claude wrote this” guards seem plausibly written by a human, it’s just that 70% of the article is in the “Claude wrote this” guard.
email: dymk (at) dymk (dot) co
woodworking: https://www.longtailwoodcraft.com/gallery.html