I’m thinking something like “this utility function is friendly, once we have solved these n specific problems; let’s create a few levels of higher intelligence, to solve these specific problems, using certain constraints (physical or motivational) to prevent things going wrong during this process”.
I’m thinking something like “this utility function is friendly, once we have solved these n specific problems; let’s create a few levels of higher intelligence, to solve these specific problems, using certain constraints (physical or motivational) to prevent things going wrong during this process”.