Lugh@futurology.todayM to Futurology@futurology.todayEnglish · 10 个月前When 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-square15linkfedilinkarrow-up180arrow-down11
arrow-up179arrow-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 · 10 个月前message-square15linkfedilink
minus-squareFearfulSalad@ttrpg.networklinkfedilinkEnglisharrow-up3·10 个月前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.
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.