misk to Technology@lemmy.worldEnglish · 6 months agoApple study exposes deep cracks in LLMs’ “reasoning” capabilitiesarstechnica.comexternal-linkmessage-square109linkfedilinkarrow-up1508arrow-down119cross-posted to: apple_enthusiast@lemmy.worldarstechnica_index@rss.ponder.cat
arrow-up1489arrow-down1external-linkApple study exposes deep cracks in LLMs’ “reasoning” capabilitiesarstechnica.commisk to Technology@lemmy.worldEnglish · 6 months agomessage-square109linkfedilinkcross-posted to: apple_enthusiast@lemmy.worldarstechnica_index@rss.ponder.cat
minus-squareSaik0@lemmy.saik0.comlinkfedilinkEnglisharrow-up1·6 months ago I’d say Gemma 2B wasn’t actually wrong I call that talking itself out of being correct.
I call that talking itself out of being correct.