AI safety is actually a sub-problem of government safety. Right now the biggest AI safety danger isn't paperclip maximization - it's that we'll tell an all powerful AI to stop making racist / sexist conclusions by any means necessary and what actions that would entail...
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
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.