Right now the scope of what an LLM can solve is pretty generic and focused. Anytime more than a class or two is involved or if the code base is more than 20 or 30 files, then even the best LLMs start to stray and lose focus. They can't seem to keep a train of thought which leads to churning way too much code.
If LLMs are going to replace real developers, they will need to accept significantly more context, they will need a way to gather context from the business at large, and some way to persist a train of thought across the life of a codebase.
I'll start to get nervous when these problems are close to being solved.