I think it becomes likely in a multipolar scenario with 10-100 Als.
One thing to take into account is that other AIs will consider such risk and keep their real preferences secret. This means that which AIs are aligned will be unknowable both for humans and for other AIs
I think it becomes likely in a multipolar scenario with 10-100 Als.
One thing to take into account is that other AIs will consider such risk and keep their real preferences secret. This means that which AIs are aligned will be unknowable both for humans and for other AIs