why does preparing for a paperclip maximizer assume Bayesianism?
"most efficient physical form" seems really unlikely to me given how many constraints evolution has been under
-
-
it's like how trains don't have legs
-
by the metric of "speed" a train is more efficient than legs, but if your metric is "turn speed" then legs are more efficient. if your metric is "steps per second" then a train's efficiency is "mu"
- 9 more replies
New conversation -
-
-
note that signals in a biological human brain are slow and if you run one in silico you can run it at a million times speed
-
(if you have the computing power)
End of conversation
New conversation -
-
-
right, the question for efficiency is always "efficient with respect to what metric"? I think human brains are more efficient at human-like thought than computers are. But I don't think people expect a general AI to have human-like thought.
Thanks. 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.
"sound alarm"? 