My lesson from these two examples is that it might be possible to make prompting “invisible” by making it part of the UI, and finetuning output for as much of the writer’s context as possible to make it more useful. Latency matters, and cost matters, which are wonderful because these tend to be “regular engineering” type problems rather than AI pr

When we speak to an AI using the perfect prompt method, we are in declamatory or dictatorial mode, telling the machine what we think it needs to know to help us.