cm0002@lemmy.world to Technology@lemmy.worldEnglish · 14 days 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-square160fedilinkarrow-up1388arrow-down146
arrow-up1342arrow-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 · 14 days agomessage-square160fedilink
minus-squareLemminary@lemmy.worldlinkfedilinkEnglisharrow-up3arrow-down1·edit-212 days agoThe reply was literally “*I* use a calculator” followed by “AI should use one too”. Are you suggesting that you’re an LLM or how did you cut a piece of cloth for yourself out of that?
The reply was literally “*I* use a calculator” followed by “AI should use one too”. Are you suggesting that you’re an LLM or how did you cut a piece of cloth for yourself out of that?