[ExI] If AI becomes conscious, how will we know?

[BillK]

On Thu, 24 Aug 2023 at 15:24, efc--- via extropy-chat
<extropy-chat at lists.extropy.org> wrote:
>
> I'd go for the good old Turing, perhaps in an updated version. Ideally I'd
> like to see independent will, volition and goals which have not been
> programmed in from the start.
>
> No, this is not fleshed out, but this would be my starting point.
>
> Best regards, Daniel
>_______________________________________________


That sounds ominous. The AGI gets to choose its own goals?
I suppose if it has surpassed human intelligence, then it won't be
asking humans for permission anyway.
That may be why Eliezer thinks we're all doomed.

BillK