I don’t know what the analogue is here. Better scaffolding? More capable LLM?
Fine tuning on examples of doing the thing you want, or making sure your new trick gets into datasets? Even more high effort than the compiler version for the amount of improves it?
Fine tuning on examples of doing the thing you want, or making sure your new trick gets into datasets? Even more high effort than the compiler version for the amount of improves it?