minus-squareEscew@lemm.eetoTechnology@lemmy.world•*Permanently Deleted*linkfedilinkEnglisharrow-up10arrow-down2·2 years 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. linkfedilink
minus-squareEscew@lemm.eetomemes@lemmy.world•Just going to make a goofy kids' movielinkfedilinkarrow-up42·2 years agoNo, being a kid is trippy enough already. linkfedilink
minus-squareEscew@lemm.eetomemes@lemmy.world•It feels wronglinkfedilinkarrow-up1·2 years agoDubya dubya dubya is slightly faster linkfedilink
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.