I think control is a meaningful concept. You could have AI that doesn’t try to alter your terminal goals. Something that just does what you want (not what you ask, since that has well-known failure modes) without trying to persuade you into something else.
The difficulty of building such a system is another question, alas.
I think control is a meaningful concept. You could have AI that doesn’t try to alter your terminal goals. Something that just does what you want (not what you ask, since that has well-known failure modes) without trying to persuade you into something else.
The difficulty of building such a system is another question, alas.