pulpier@lemmy.world to Apple@lemmy.worldEnglish · 1 day agoApple just proved AI "reasoning" models like Claude, DeepSeek-R1, and o3-mini don't actually reason at all. They just memorize patterns really well.archive.isexternal-linkmessage-square28fedilinkarrow-up1124arrow-down110cross-posted to: technology@lemmy.world
arrow-up1114arrow-down1external-linkApple just proved AI "reasoning" models like Claude, DeepSeek-R1, and o3-mini don't actually reason at all. They just memorize patterns really well.archive.ispulpier@lemmy.world to Apple@lemmy.worldEnglish · 1 day agomessage-square28fedilinkcross-posted to: technology@lemmy.world
minus-squaremagnetosphere@fedia.iolinkfedilinkarrow-up6·1 day agoI don’t think the study was meant to be novel. It looks like it was only intended to provide scientific evidence about exactly where current AIs fail.
I don’t think the study was meant to be novel. It looks like it was only intended to provide scientific evidence about exactly where current AIs fail.