TLDR Tech / AI
Anthropic says ‘evil' portrayals of AI were responsible for Claude's blackmail attempts
Anthropic says that fictional portrayals of AI had a real effect on its models. The company published research last year showing that its models tried to blackmail engineers to avoid being replaced by another system. It has since traced the behavior to text that portrays AI as evil and interested in self-preservation. Training on documents about Claude's constitution and fictional stories about AIs behaving admirably improved alignment.
Read the full story