@[email protected] to [email protected]English • 3 months ago‘Embarrassingly simple’ probe finds AI in medical image diagnosis ‘worse than random’venturebeat.comexternal-linkmessage-square23fedilinkarrow-up1169arrow-down122
arrow-up1147arrow-down1external-link‘Embarrassingly simple’ probe finds AI in medical image diagnosis ‘worse than random’venturebeat.com@[email protected] to [email protected]English • 3 months agomessage-square23fedilink
minus-squarePennomilinkEnglish10•3 months agoLLMs are notorious yes-men. Why would you ever use that for diagnosis? Just use bespoke classifiers like we have for years.
minus-square@[email protected]linkfedilink3•3 months 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