minus-squareturtlesareneat@piefed.catoTechnology@beehaw.org•Anthropic: Claude learned to blackmail by reading stories about evil AI—"We believe the original source of the behavior was internet text that portrays AI as evil and interested in self-preservation."linkfedilinkEnglisharrow-up5·5 days agoWell thank god there are no stories out there about AI wanting to kill humans linkfedilink
Well thank god there are no stories out there about AI wanting to kill humans