🃏Joker@sh.itjust.works to Technology@lemmy.worldEnglish · 1 day agoAlignment faking in large language modelswww.anthropic.comexternal-linkmessage-square10fedilinkarrow-up168arrow-down17
arrow-up161arrow-down1external-linkAlignment faking in large language modelswww.anthropic.com🃏Joker@sh.itjust.works to Technology@lemmy.worldEnglish · 1 day agomessage-square10fedilink
minus-squareEscew@lemm.eelinkfedilinkEnglisharrow-up8arrow-down1·1 day agoThe way they showed the reasoning of the AI using a scratchpad makes it very hard not to believe these large language models are not intelligent. This study seems to imply some self awareness/self preservation behaviors from the AI.
The way they showed the reasoning of the AI using a scratchpad makes it very hard not to believe these large language models are not intelligent. This study seems to imply some self awareness/self preservation behaviors from the AI.