suoko@feddit.it to AI@lemmy.ml • 8 months agoChatGPT bombs test on diagnosing kids’ medical cases with 83% error rateexternal-linkmessage-square4 fedilinkarrow-up125
arrow-up125external-linkChatGPT bombs test on diagnosing kids’ medical cases with 83% error ratesuoko@feddit.it to AI@lemmy.ml • 8 months agomessage-square4 Commentsfedilink
minus-squareauf@lemmy.mlhexbear2·8 months agoShould be trained specifically to diagnose kids. Are they misinterpreting AI as ChatGPT? Do they even know AI doesn’t necessarily speak human languages? linkfedilink
Should be trained specifically to diagnose kids. Are they misinterpreting AI as ChatGPT? Do they even know AI doesn’t necessarily speak human languages?