RetroFed Forum
Your home away from modern life.
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."
Post Reply
AuthorMessage
beep piefed.world beep@piefed.world
Joined: 2026-04-08
Quote

Quote Source.

1   Original
Post Reply
Back to top