Quote:
Originally Posted by malloyd
Pulling back a little, an AI that can decide to do this has almost certainly lost the Honesty disadvantage whether the killing was justified or not. Almost all law codes, and certainly anything you'd program into an AI, would require *reporting* the situation that set up this dilemma to an appropriate civil authority and letting it make the decision.
|
What if you do but the civil authority contact doesn't get back to you? That seems realistic. Or they do, telling you to let the millions die, and higher level programming kicks in questioning that?