Wait, that doesn’t make any sense. I am confident all these people totally think that aligning Superintelligence is a critical first try problem the way Eliezer is talking about here.
They may think it’s critical but not very firsty, i.e. sufficiently similar to / comparable to / generalizable from previous tries.
Wait, that doesn’t make any sense. I am confident all these people totally think that aligning Superintelligence is a critical first try problem the way Eliezer is talking about here.
They may think it’s critical but not very firsty, i.e. sufficiently similar to / comparable to / generalizable from previous tries.