there might be better words to describe that it doesn’t really has the same boundaries we assume it has.

You need to go back and research AI safety long before LLMs were a thing. Any complex goal driven system will have outcomes that cannot be predicted. Saying "it's a mathematical model" belies your ignorance of behavior in complex systems. Very tiny changes in initial conditions can have vastly different outcome in results and you don't have enough entropy in the visible universe to test them all.

Sure I'd also agree with that, some are so complex we can't understand, but that's still our relying on it then

Blind optimisers without human qualities like ethics are pretty much the perfect example of what ruthless means.