Zerush@lemmy.ml to Technology@lemmy.ml · 23 hours agoAnthropic's new AI model turns to blackmail when engineers try to take it offline | TechCrunchtechcrunch.comexternal-linkmessage-square11linkfedilinkarrow-up133arrow-down110cross-posted to: news@lemmy.worldtechnology@lemmy.zipfuturology
arrow-up123arrow-down1external-linkAnthropic's new AI model turns to blackmail when engineers try to take it offline | TechCrunchtechcrunch.comZerush@lemmy.ml to Technology@lemmy.ml · 23 hours agomessage-square11linkfedilinkcross-posted to: news@lemmy.worldtechnology@lemmy.zipfuturology
minus-squareZerush@lemmy.mlOPlinkfedilinkarrow-up6·23 hours agoI don’t know what scares me more, that the AI itself blackmail to avoid desconnection or it is trained to do it.
minus-squaresupersquirrel@sopuli.xyzlinkfedilinkarrow-up18·20 hours agoThe people in charge of these companies should scare you the most.
I don’t know what scares me more, that the AI itself blackmail to avoid desconnection or it is trained to do it.
The people in charge of these companies should scare you the most.