Posts

Honolulu, HI – ACX Meetups Everywhere 2022 2022-08-24T22:59:31.553Z
Honolulu Rationality September 3, 2022 Meetup / ACX Meetups Everywhere 2022-08-13T23:45:56.196Z
Honolulu Rationality July 30, 2022 Meetup 2022-06-27T17:31:26.104Z
Honolulu Rationality July 9, 2022 Meetup 2022-06-27T17:27:15.118Z
Honolulu Rationality June 2022 Meetup 2022-05-29T19:01:32.180Z
Honolulu Rationality May 2022 Meetup 2022-04-30T17:24:33.666Z

Comments

Comment by mpopv on AGI Safety FAQ / all-dumb-questions-allowed thread · 2022-06-08T19:11:39.172Z · LW · GW

Assuming we have control over the utility function, why can't we put some sort of time-bounding directive on it?

i.e. "First and foremost, once [a certain time] has elapsed, you want to run your shut_down() function. Second, if [a certain time] has not yet elapsed, you want to maximize paperclips."

Is that problem that the AGI would want to find ways to hack around the first directive to fulfill the second directive? If so, that would seem to at least narrow the problem space to "find ways of measuring time that cannot be hacked before the time has elapsed".