We don't yet know the "load bearing" or "delve" or "not X. Not Y. Just..." Clichés of video AI - at least I don't know. But given it's instruction tuned, we can be confident they will be there, and that the breadth of what it can generate for a given prompt will have extremely low diversity compared to its training data.
One of the big dead giveaways for AI videos is the sequence of slow pan shots without any sort of real action or focus. Once you start seeing it in a few of them, you'll start seeing it in _all_ of them. Just shot after shot of a slow pan of a scene with minimal action happening in only a few areas.