Wait this is new? Large context models figure out the architecture of the request. Miss sized models plan out each requirement, and smaller models implement a tightly detailed task? Isn't this the standard approach?

> Miss sized models plan out each requirement, and smaller models implement a tightly detailed task? Isn't this the standard approach?

It is, but the article is suggesting something different. The central idea is to use /prewalk to load slightly edited context from the more expensive model into the one, so that the cheaper model doesn't burn tokens reading all the files again.