Well, capabilities are more about having large effects, and alignment is about having effects that are desirable to the principal. You can imagine a 2x2 matrix with aligned/unaligned, highly capable / slightly capable. Aligned + highly capable is the best, unaligned + highly capable is the worst.
One way to think about it is, AI can be made to have enough short term alignment that we are incentivized to hand over long-term powers to it, before we’ve solved the problem of long term alignment. If those powers are long term enough, that handover would be irreversible.
Because both essentially are the same thing: alignment is about AI doing what I want—and capabilities are about Ai doing what I want?
Well, capabilities are more about having large effects, and alignment is about having effects that are desirable to the principal. You can imagine a 2x2 matrix with aligned/unaligned, highly capable / slightly capable. Aligned + highly capable is the best, unaligned + highly capable is the worst.
One way to think about it is, AI can be made to have enough short term alignment that we are incentivized to hand over long-term powers to it, before we’ve solved the problem of long term alignment. If those powers are long term enough, that handover would be irreversible.