@[email protected] to [email protected] • 1 year agoAnthropic's new AI model turns to blackmail when engineers try to take it offline | TechCrunchtechcrunch.comexternal-linkmessage-square11fedilinkarrow-up136
arrow-up136external-linkAnthropic's new AI model turns to blackmail when engineers try to take it offline | TechCrunchtechcrunch.com@[email protected] to [email protected] • 1 year agomessage-square11fedilink
minus-square@[email protected]OPlinkfedilink6•1 year agoI don’t know what scares me more, that the AI itself blackmail to avoid desconnection or it is trained to do it.
minus-square@[email protected]linkfedilink20•1 year 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.