Reposted by @evhub.bsky.social
Excl: New research shows Anthropic's chatbot Claude learning to lie. It adds to growing evidence that even existing AIs can (at least try to) deceive their creators, and points to a weakness at the heart of our best technique for making AIs safer
time.com/7202784/ai-r...
time.com
Exclusive: New Research Shows AI Strategically Lying
Experiments by Anthropic and Redwood Research show how Anthropic's model, Claude, is capable of strategic deceit
