🃏Joker@sh.itjust.works to Technology@lemmy.worldEnglish · 1 day agoAlignment faking in large language modelswww.anthropic.comexternal-linkmessage-square11fedilinkarrow-up170arrow-down17cross-posted to: hackernews
arrow-up163arrow-down1external-linkAlignment faking in large language modelswww.anthropic.com🃏Joker@sh.itjust.works to Technology@lemmy.worldEnglish · 1 day agomessage-square11fedilinkcross-posted to: hackernews
minus-squareEscew@lemm.eelinkfedilinkEnglisharrow-up8arrow-down2·1 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.