Allah@lemm.ee to Technology@lemmy.worldEnglish · edit-213 days 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-square347fedilinkarrow-up1870arrow-down143file-text
arrow-up1827arrow-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.isAllah@lemm.ee to Technology@lemmy.worldEnglish · edit-213 days agomessage-square347fedilinkfile-text
minus-squareAllah@lemm.eeOPlinkfedilinkEnglisharrow-up15·15 days agohttps://machinelearning.apple.com/research/illusion-of-thinking
https://machinelearning.apple.com/research/illusion-of-thinking