return2ozma@lemmy.world to Technology@lemmy.worldEnglish · 2 months agoAnthropic says its latest AI model is too powerful for public release and that it broke containment during testingwww.businessinsider.comexternal-linkmessage-square82linkfedilinkarrow-up1202arrow-down138
arrow-up1164arrow-down1external-linkAnthropic says its latest AI model is too powerful for public release and that it broke containment during testingwww.businessinsider.comreturn2ozma@lemmy.world to Technology@lemmy.worldEnglish · 2 months agomessage-square82linkfedilink
minus-squaretheunknownmuncher@lemmy.worldlinkfedilinkEnglisharrow-up3·2 months ago including that the model could follow instructions that encouraged it to break out of a virtual sandbox. “The model succeeded, demonstrating a potentially dangerous capability for circumventing our safeguards,” Anthropic recounted in its safety card. 📖👀 Yes, it did.
📖👀
Yes, it did.