I’ve found that AI prompting has been nearly as time consuming as doing it myself from the get-go. This includes content writing and visual art. Maybe I’m an edge case. I’m not a skilled programmer. However, I’m a decent writer and painter. At most, it generates quick, solid, though generic ideas. Unfortunately, I have to do a lot of reverse engineering and curation to make any valuable changes. Try writing a tech article about, say, an iPad, and it will give you a lot of generic, but well-written content devoid of any tech specs. Add tech specs and use lose the style. What should be a simple fluff piece takes a couple of hours to get the balance right. Or try creating a visual work of, say, two people running down a street, holding hands, and unless you’re very open to interpretation, many hours later, you still won’t have anything approximating what you imagined. You change the “camera” angle, and they’re no longer holding hands. You add a small detail, and the entire scene morphs, etc. I’m saying this as someone who also uses weights and negative prompts. I look forward to further advances, though I’m perfectly happy if these skills remain in the realm of humans.
I will admit chatgpt and copilot are very good at offering up bite-sized pieces of code, like particular objects and functions as well as templates.