pulpier@lemmy.world to Apple@lemmy.worldEnglish · 3 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-up124arrow-down13cross-posted to: [email protected]
arrow-up121arrow-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 · 3 months agomessage-square28linkfedilinkcross-posted to: [email protected]
minus-squareYtA4QCam2A9j7EfTgHrH@infosec.publinkfedilinkarrow-up4·3 months agoBut Sam Altman called it a “reasoning model.” Would he lie?!
But Sam Altman called it a “reasoning model.” Would he lie?!