Coherence arguments imply a force for goal-directed behavior
blog.aiimpacts.org
By Katja Grace, 25 March 2021 [Epistemic status: my current view, but I haven’t read all the stuff on this topic even in the LessWrong community, let alone more broadly.] There is a line of thought that says that advanced AI will tend to be ‘goal-directed’—that is, consistently doing whatever makes certain favored outcomes more likely—and that this is to do with the ‘coherence arguments’.
Coherence arguments imply a force for goal-directed behavior
Coherence arguments imply a force for…
Coherence arguments imply a force for goal-directed behavior
By Katja Grace, 25 March 2021 [Epistemic status: my current view, but I haven’t read all the stuff on this topic even in the LessWrong community, let alone more broadly.] There is a line of thought that says that advanced AI will tend to be ‘goal-directed’—that is, consistently doing whatever makes certain favored outcomes more likely—and that this is to do with the ‘coherence arguments’.