misk to Technology@lemmy.worldEnglish · 1 month agoApple study exposes deep cracks in LLMs’ “reasoning” capabilitiesarstechnica.comexternal-linkmessage-square109fedilinkarrow-up1509arrow-down119cross-posted to: apple_enthusiast@lemmy.worldarstechnica_index@rss.ponder.cat
arrow-up1490arrow-down1external-linkApple study exposes deep cracks in LLMs’ “reasoning” capabilitiesarstechnica.commisk to Technology@lemmy.worldEnglish · 1 month agomessage-square109fedilinkcross-posted to: apple_enthusiast@lemmy.worldarstechnica_index@rss.ponder.cat
minus-squaremiskOPlinkfedilinkEnglisharrow-up11·1 month agoGiven the use cases they were benchmarking I would be very surprised if they were any better.
Given the use cases they were benchmarking I would be very surprised if they were any better.