@Meaningness @voidfraction @admittedlyhuman I'd be interested in the outcome of that experiment
@admittedlyhuman @niftierideology Yes; what current NNs are good at is finding simple solutions to problems that looked hard but weren’t, >
-
-
@admittedlyhuman@niftierideology > by (in effect) exploring a huge search space of simple solutions with massive parallelism. -
@admittedlyhuman@niftierideology What they are probably not good at is solving actually hard problems. - 14 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.