namely the cases where the AI is trying really hard to be friendly, but doing it in a way that we did not intend.
If the AI knows what friendly is or what mean means, than your conclusion is trivially true. The problem is programming those in—that’s what FAI is all about.
If the AI knows what friendly is or what mean means, than your conclusion is trivially true. The problem is programming those in—that’s what FAI is all about.