Working with AI is still strange territory. We reach for metaphors: manager, intern, editor, surgeon. Each gets close, but none explain the back-and-forth dance of giving inputs, interpreting outputs, and adjusting course as you work alongside a machine. We want scale, but we also want the output to reflect our judgment, our standards, and our voice. It is not just about producing more; it is about making sure what is produced still feels like us.
The Old Metaphors
Manager: Too detached. You end up supervising outputs instead of shaping them.
Intern: Too one-way. You spend more time teaching and correcting than creating.
Editor: Too reactive. You polish what already exists instead of driving direction.
