@camlorn38 Didn't think it was. It does seem like we'll need a model like this if we don't want our AIs to be either murderous or slaves.
@camlorn38 @FullPresence A military AI is a more dangerous starting point than a paperclip maximizer, not less.
-
-
@chaosprime@FullPresence True, I could buy that. The paperclip maximizer might give us an additional week. -
@camlorn38@FullPresence Ha, from http://wiki.lesswrong.com/wiki/Paperclip_maximizer …: "Human values don't spontaneously emerge in a generic optimization process." - 4 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.