That doesn’t apply in this scenario. If CEOs start trying to emulate ethics in order to avoid being 86’d, we still get a good outcome.

An issue arises when the metric isn’t a good proxy for the property being measured. But ethics would not be a simple numeric target. The comment above talked about a “score”, but the question is what goes into that score. It would need to be a list of items related to topics like discrimination, advocacy of inequality, tendency to circumvent regulations, etc. Set it up correctly, and even a CEO who’s willing to “fake it” would end up being better than most major company CEOs in e.g. finance, tech, or healthcare today.