beep@piefed.world to Technology@beehaw.orgEnglish · 5 months agoAnthropic: 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."alignment.anthropic.comexternal-linkmessage-square7linkfedilinkarrow-up112arrow-down14file-text
arrow-up18arrow-down1external-linkAnthropic: 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."alignment.anthropic.combeep@piefed.world to Technology@beehaw.orgEnglish · 5 months agomessage-square7linkfedilinkfile-text
cross-posted from: https://piefed.world/c/tech/p/1099863/anthropic-claude-learned-to-blackmail-by-reading-stories-about-evil-ai-we-believe-the-or Quote Source.
minus-squarespit_evil_olive_tips@beehaw.orglinkfedilinkarrow-up7·5 months ago Anthropic: Claude learned yeah I’m gonna stop you right there
yeah I’m gonna stop you right there