🃏Joker@sh.itjust.works to Technology@lemmy.worldEnglish · 12 days agoAlignment faking in large language modelswww.anthropic.comexternal-linkmessage-square12fedilinkarrow-up180arrow-down17
arrow-up173arrow-down1external-linkAlignment faking in large language modelswww.anthropic.com🃏Joker@sh.itjust.works to Technology@lemmy.worldEnglish · 12 days agomessage-square12fedilink
minus-squareEscew@lemm.eelinkfedilinkEnglisharrow-up10arrow-down2·12 days 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.