In a month or three we’ll have the sensible approach, which is smaller cheaper fast models optimized for looking at a query and identifying which skills / context to provide in full to the main model.

It’s really silly to waste big model tokens on throat clearing steps

▲

Calavar 4 hours ago | parent [-]

I thought most of the major AI programming tools were already doing this. Isn't this what subagents are in Claude code?

	▲	MillionOClock 4 hours ago \| parent [-]
		I don't know about Claude Code but in GitHub Copilot as far as I can tell the subagents are just always the same model as the main one you are using. They also need to be started manually by the main agent in many cases, whereas maybe the parent comment was referring about calling them more deterministically?