The magic sauce in intelligence is context-awareness. If a prompt is somewhat general ("make me a calculator") an AI should either ask questions, or make reasonable assumptions, or both.

IME LLMs often make reasonable assumptions, but sometimes they don't and you have to backtrack and say "No, what I meant was..."

When the process works it's almost magical because the LLM successfully anticipates your needs, and implements your request in a much fuller way than you might have done yourself.

When it doesn't it makes a mess you have to clean up.

But generally I've been impressed by how well the leading LLMs will Do The Thing from a brief description, interpolating useful and correct details without being told to.

Compilers don't work like that. They're translators, not (entry level) inventors with independent agency.