One of the few paths to victory I see is having a weakly aligned weak AGI which is not capable of recursive self-improvement and using it as a research assistant to help us solve the hard version of alignment. I don’t think this has a high probability of working, but it seems probably worth trying.
One of the few paths to victory I see is having a weakly aligned weak AGI which is not capable of recursive self-improvement and using it as a research assistant to help us solve the hard version of alignment. I don’t think this has a high probability of working, but it seems probably worth trying.