> So you can just as easily turn the analogy around and say people are the "cheap but worse" option.

No, because this is a factual question with a factual answer. You need to actually know which is more dangerous.

> FWIW, we have been able to create processes to manage risks with unpredictable humans, why couldn't we with AI ¯\\_(ツ)_/¯

Because humans and AI are different? We are much better at predicting when humans will be wrong than with AI, for one.