I don't get your point. We can train the model with the aim that it understands ethics. Problem solved if this works; back to the drawing board if it doesn't (note that the model should generalize here, as you'd expect from a human; this is probably the hard part for an AI when it comes to ethics).
Is this about the word "understand"? We're past that discussion ...
Is this about the word "understand"? We're past that discussion ...