I haven't been professionally responsible for code since before AI started eating everything, and haven't touched AI in the meantime. Is this representative of the BS that everyone else here puts up with on a day-to-day basis? Did we collectively burn trillions of dollars for this?

Sometimes, yes, but obviously not everyone. I suspect that it depends what you're doing and how. Perhaps the AI has more difficulty understanding what some people want than what others want. I certainly have had a milder version of this and it neutralises the value of the tool because it keeps trying to do things you don't want in a way you don't want it to do them. I get annoyed at having to write huge explanations of how to do something and end up doing it myself sometimes.