I think one of the best use cases of AI is as a natural language interface to programming. The syntax of a programming language is an opinionated part of its design that often adds to the complexity of learning the language.

Everything old is new again. The reason natural language never caught on for programming, is that natural language is inherently unsuitable for the task of formulating precise and unambiguous instructions for a machine.

Numerous attempts have been made in past 70 years, but we landed on the compromise that is high level programming languages with their (mostly) well-defined syntax and semantic rules.

If you look outside of the world of programming you'll find that the same is true for every craft and profession that requires precision and unambiguity. Cooking, logistics, military, carpentry, mechanical engineering, law, medicine, etc. all have their own domain specific languages for describing tasks, procedures, and tools. Heck, even sufficiently large organisations have their own internal languages and terms for that reason.

You can let it help with syntax, but you can't rely on it to understand precise semantics.

SQL is the worst offender here: LLMs are very good at remembering its awful syntax, but very bad at writing nontrivial queries.