Your expertise and point of view are feeding the model.
If you had expertise, you wouldn't be vibe coding, because then your product would be much better than the slop the LLM is capable of producing.
How does that make sense? The expertise is what allows me to tell the LLM what to do in the first place, inspect its outputs, and iterate, which is still faster than coding by hand.
Actually the slop here is your insta-vibed verbiage that you are parroting. No LLM required.