pulpier@lemmy.world to Apple@lemmy.worldEnglish · 1 month 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-up1129arrow-down110cross-posted to: [email protected]
arrow-up1119arrow-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 month agomessage-square28fedilinkcross-posted to: [email protected]
minus-squareJimbabwe@lemmy.worldlinkfedilinkarrow-up9·1 month ago No one thought that modern AI could solve arbitrarily complex logic problems, or even that modern AI was particularly good at formal reasoning. haha, except pretty much everyone in the c-suite at the company I work for.
haha, except pretty much everyone in the c-suite at the company I work for.