pulpier@lemmy.world to Apple@lemmy.worldEnglish · 2 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-square28linkfedilinkarrow-up1128arrow-down110cross-posted to: technology@lemmy.world
arrow-up1118arrow-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 · 2 months agomessage-square28linkfedilinkcross-posted to: technology@lemmy.world
minus-square6nk06@sh.itjust.workslinkfedilinkarrow-up6·2 months ago No one thought that modern AI could solve arbitrarily complex logic problems Except half the threads on Hacker News and Lobsters and LinkedIn.
Except half the threads on Hacker News and Lobsters and LinkedIn.