You can think of LLMs as a higher level language for whatever programming language you are using, but informal with ambiguous grammar.

I don't think that works. The fact that it can produce different output for the same input, usage of tools etc. don't really fit into the analogy or mental model.

What has worked for me is treating it like an enthusiastic intern with his foot always on the accelerator pedal. I need to steer and manage the brakes otherwise, it'll code itself off a cliff and take my software with it. The most workable thing is a pair programmer. For trivial changes and repeatedly "trying stuff out", you don't need to babysit. For larger pieces, it's good to make each change small and review what it's trying.