pulpier@lemmy.world to Apple@lemmy.worldEnglish · 4 months 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-square27linkfedilinkarrow-up1128arrow-down111
arrow-up1117arrow-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 · 4 months agomessage-square27linkfedilink
minus-squarea1studmuffin@aussie.zonelinkfedilinkEnglisharrow-up2·4 months agoI’d love to see these complexity results compared against humans for a laugh.
I’d love to see these complexity results compared against humans for a laugh.