The reason this is a difficult question is that we don’t know how hard alignment will be. Opinions from different people with best-in-class expertise and time-on-task disagree wildly.
Therefore I’d argue that we should throw effort and funding into resolving that question by putting the reasoning processes of the relevant experts to wider scrutiny, and do a more systematic job of evaluating them.
Funding comes from a different resource pool than regulation, so you might mean which one should get your advocacy efforts. The same arguments apply to both of them, and to the meta-alignment question.
The reason this is a difficult question is that we don’t know how hard alignment will be. Opinions from different people with best-in-class expertise and time-on-task disagree wildly.
Therefore I’d argue that we should throw effort and funding into resolving that question by putting the reasoning processes of the relevant experts to wider scrutiny, and do a more systematic job of evaluating them.
Funding comes from a different resource pool than regulation, so you might mean which one should get your advocacy efforts. The same arguments apply to both of them, and to the meta-alignment question.