Re:Training for one trillion parameter model backed by Intel...
by ben_w on Friday November 24, 2023 @01:05PM
(#38406534)
We don't have any existent examples of AGI from which to be as confident as you are about what they will "want".
And I don't think we need sentience for AGI, so "want" may be the wrong term anyway. You could argue that the reward function is close enough ("do submarines swim?" etc.), but a human-made reward function is almost certainly going to be designed to be as close to aligned with our interests as we can manage.
And I don't think we need sentience for AGI, so "want" may be the wrong term anyway. You could argue that the reward function is close enough ("do submarines swim?" etc.), but a human-made reward function is almost certainly going to be designed to be as close to aligned with our interests as we can manage.