I didn't make clear I was responding to your question:

"Where do my 20 years of software dev experience fit into this except beyond imparting my aesthetic preferences?"

Anyway, I think you kind of unintentionally proved my point. These two examples are pretty trivial as far as software goes, and it enabled someone with a little technical experience to implement them where before they couldn't have.

They work well because:

a) the full implementation for these apps don't even fill up the AI context window. It's easy to keep the LLM on task.

b) it's a tutorial style-app that people often write as "babby's first UI widget", so there are thousands of examples of exactly this kind of thing online; therefore the LLM has little trouble summoning the correct code in its entirety.

But still, someone with zero technical experience is going to be immediately thwarted by the prompts you provided.

Take the first one "I want a menubar app that shows me the current weather".

https://chatgpt.com/share/693b20ac-dcec-8001-8ca8-50c612b074...

ChatGPT response: "Nice — here's a ready-to-run macOS menubar app you can drop into Xcode..."

She's already out of her depth by word 11. You expect your mom to use Xcode? Mine certainly can't. Even I have trouble with Xcode and I use it for work. Almost every single word in that response would need to be explained to her, it might as well be a foreign language.

Now, the LLM could help explain it to her, and that's what's great about them. But by the time she knows enough to actually find the original response actionable, she would have gained... knowledge and experience enough to operate it just to the level of writing that particular weather app. Though having done that, it's still unreasonable to now believe she could then use the LLM to write a bytecode compiler, because other people who have a Ph.D. in CS can. The LLM doesn't level the playing field, it's still lopsided toward the Ph.D.s / senior devs with 20 years exp.