/architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds 1 month ago
@DanMcInerney Thank you for sharing this! Using a larger model for planning and a cheaper, smaller model for execution is a smart way to save tokens and seems like the way to go in general.
I wanted to see what would happen if Claude delegated work to pi wiht a model like Deepseek, so I forked your repo and tried it out. It's working really well so far. https://github.com/pcomans/architect-loop-pi