Lugh@futurology.todayM to Futurology@futurology.todayEnglish · 20 days agoWhen AI is tested on questions it can't model from pre-existing answers on the internet, it only scores 10% in the test.qz.comexternal-linkmessage-square15fedilinkarrow-up179arrow-down11
arrow-up178arrow-down1external-linkWhen AI is tested on questions it can't model from pre-existing answers on the internet, it only scores 10% in the test.qz.comLugh@futurology.todayM to Futurology@futurology.todayEnglish · 20 days agomessage-square15fedilink
minus-squareFearfulSalad@ttrpg.networklinkfedilinkEnglisharrow-up3·20 days agoThat reads like the sort of thing Wolfram Alpha was designed to absolutely obliterate, if only the raw data representing each of those keywords had been loaded in.
That reads like the sort of thing Wolfram Alpha was designed to absolutely obliterate, if only the raw data representing each of those keywords had been loaded in.