There is no known way of programming goals into an advanced optimizer, only outwardly observable behaviors of which we have no idea why they are being carried out or what motivates them.
If true, what do we conclude? That an optimiser will have its own goals, or that no AI will have any goals ? (Probably meaning that there are no possible optimisers, since optimisers need goals.)
An artificial super-optimizer is likely to be developed soon.
OK, you believe in optimisers … so where do they get their goals from?
If true, what do we conclude? That an optimiser will have its own goals, or that no AI will have any goals ? (Probably meaning that there are no possible optimisers, since optimisers need goals.)
OK, you believe in optimisers … so where do they get their goals from?