I don't think it has much to do with how "complex or not" it is, but rather how common it is.

It can completely fail on very simple things that are just a bit obscure, so it has too little training data.

And it can do very complex things if there's enough training data on those things.

I've also found it useful for simple Python scripts when I need to analyze data. I don't use pandas/scipy/numpy/matplotlib enough to remember the syntax and library functions. With vibe coding it, I can have a script in minutes for reading a csv with weird timestamps, scale some of the channels, filter out noise or detrending, perform a Fourier transform, and do a curve fit towards a model.

But then obviously I know every intermediate step I want to do.

When I want to be lazy and make some simple excel macros is about the most iv trusted it with that it manages to do with out fucking up and taking more time then just doing it my self.