Aligned with the sum total of the behavior of a given human across all seconds of their life
More likely to be able to say “yes” to something like:
Aspirationally aligned with (i.e. would willingly push a button to sacrifice the parts of me that are in contradiction with) the best of what humans have managed to explicitly write down as their highest values
Aspirationally aligned with the best five percent of human behavior
I would be extremely reluctant to outsource my moral compass or decisionmaking power to almost any extant human.
I try to behave such that other people would be [substantially less extremely reluctant than baseline] to outsource their moral compasses or decisionmaking power to me, though I suspect most people both would and should still be extremely reluctant in an absolute sense.
Strong no on versions of “aligned” such as:
Aligned with the weighted average of humans
Aligned with the median of humans
Aligned with the sum total of the behavior of a given human across all seconds of their life
More likely to be able to say “yes” to something like:
Aspirationally aligned with (i.e. would willingly push a button to sacrifice the parts of me that are in contradiction with) the best of what humans have managed to explicitly write down as their highest values
Aspirationally aligned with the best five percent of human behavior
I would be extremely reluctant to outsource my moral compass or decisionmaking power to almost any extant human.
I try to behave such that other people would be [substantially less extremely reluctant than baseline] to outsource their moral compasses or decisionmaking power to me, though I suspect most people both would and should still be extremely reluctant in an absolute sense.