You adapted to the underdeveloped UX of wonky proof-of-concepts built by researchers, working around shortcomings that will be ironed out once genuine sofware developers start releasing actual products.
I'm not so sure how much they will be ironed out. If the product only has a button you can press then maybe, but if it lets you enter text then I think knowing how to prompt will be useful.
The reason I believe this is because one of the greatest strengths of these AI models is to take in arbitrary text. If you take away that ability then you just end up with a complicated branching system that could've existed before.
> The reason I believe this is because one of the greatest strengths of these AI models is to take in arbitrary text.
And they will get better at making sense of vague questions, and start asking for clarification, without the need for the black magic of a prompt wizard.
The prompt engineer can soon be replaced with a fine-tuned LLM. It's a thing already for SD prompts. No more need to know ridiculous magic prompt tokens.
The reason I believe this is because one of the greatest strengths of these AI models is to take in arbitrary text. If you take away that ability then you just end up with a complicated branching system that could've existed before.