Robin Hanson wrote:
> > The best that we can do is teach it how do deduce its
> > own rules, and hope it comes up with a moral system requires it to be
> > to fellow sentients..
> Well we could do a little more; we might create lots of different AIs
> and observer how they treat each other in contained environments. We
> then repeatedly select the ones whose behavior we deem "moral." And once
> we have creatures whose behavior seems stably "moral" we could release
> to participate in the big world.
> However, I'd expect evolutionary pressures to act again out in the big
> and so our only real reason for confidence in continued "moral" behavior
> would be expectations that such behavior would be rewarded in a world when
> most other creatures also act that way..
If we can do this, the project has failed. Even a mildly Transhuman AI will be able to deduce what is going on and fool us about its morality. A Power will find some way around any security we can create, either through coding or social engineering.