cm0002@lemmy.world to Technology@lemmy.worldEnglish · 23 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-square110fedilinkarrow-up1313arrow-down133
arrow-up1280arrow-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 · 23 hours agomessage-square110fedilink
minus-squareNot_mikey@slrpnk.netlinkfedilinkEnglisharrow-up3·14 hours agoI think a lot of services are doing this behind the scenes already. Otherwise chatgpt would be getting basic arithmetic wrong a lot more considering the methods the article has shown it’s using.
I think a lot of services are doing this behind the scenes already. Otherwise chatgpt would be getting basic arithmetic wrong a lot more considering the methods the article has shown it’s using.