cm0002@lemmy.world to Technology@lemmy.worldEnglish · 19 hours agoAnthropic has developed an AI 'brain scanner' to understand how LLMs work and it turns out the reason why chatbots are terrible at simple math and hallucinate is weirder than you thoughtwww.pcgamer.comexternal-linkmessage-square95fedilinkarrow-up1273arrow-down121
arrow-up1252arrow-down1external-linkAnthropic has developed an AI 'brain scanner' to understand how LLMs work and it turns out the reason why chatbots are terrible at simple math and hallucinate is weirder than you thoughtwww.pcgamer.comcm0002@lemmy.world to Technology@lemmy.worldEnglish · 19 hours agomessage-square95fedilink
minus-squareCarrolade@lemmy.worldlinkfedilinkEnglisharrow-up1·15 hours agoExactly. It’s sort of like a massively scaled up example of the blind man and the elephant.
Exactly. It’s sort of like a massively scaled up example of the blind man and the elephant.