ylai@lemmy.ml to AI@lemmy.mlEnglish · 20 days ago‘Embarrassingly simple’ probe finds AI in medical image diagnosis ‘worse than random’venturebeat.comexternal-linkmessage-square26fedilinkarrow-up1184arrow-down119
arrow-up1165arrow-down1external-link‘Embarrassingly simple’ probe finds AI in medical image diagnosis ‘worse than random’venturebeat.comylai@lemmy.ml to AI@lemmy.mlEnglish · 20 days agomessage-square26fedilink
minus-squarePennomi@lemmy.worldlinkfedilinkEnglisharrow-up10·20 days agoLLMs are notorious yes-men. Why would you ever use that for diagnosis? Just use bespoke classifiers like we have for years.
minus-squareLojcs@lemm.eelinkfedilinkarrow-up3·20 days agoBecause some researcher wanted to document what would happen and a journalist thought writing about that would get many clicks
LLMs are notorious yes-men. Why would you ever use that for diagnosis? Just use bespoke classifiers like we have for years.
Because some researcher wanted to document what would happen and a journalist thought writing about that would get many clicks