Maybe I don't understand the reasoning or the premise, but subagents can make writing code, experimenting way faster and you don't have to manage them, a large and smart model will manage them for you.
Also there are harnesses (e.g. omp) which are using multiple LLMs debating, questioning, reviewing other LLMs output and you get a pretty good result at the end that way, which makes your job of reviewing them faster too.
Also there are harnesses (e.g. omp) which are using multiple LLMs debating, questioning, reviewing other LLMs output and you get a pretty good result at the end that way, which makes your job of reviewing them faster too.