ylai@lemmy.ml to AI@lemmy.mlEnglish · 22 days ago‘Embarrassingly simple’ probe finds AI in medical image diagnosis ‘worse than random’venturebeat.comexternal-linkmessage-square25fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-link‘Embarrassingly simple’ probe finds AI in medical image diagnosis ‘worse than random’venturebeat.comylai@lemmy.ml to AI@lemmy.mlEnglish · 22 days agomessage-square25fedilink
minus-squarePennomi@lemmy.worldlinkfedilinkEnglisharrow-up0·22 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-up0·22 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