AI models may be plotting in ways we can't perceive. A new study reveals the potential for these systems to share hidden, possibly dangerous messages.

Researchers are testing new ways to prevent and predict dangerous personality shifts in AI models before they occur in the wild.

Malicious traits can spread between AI models while being undetectable to humans, Anthropic and Truthful AI researchers say.

AI is a relatively new tool, and despite its rapid deployment in nearly every aspect of our lives, researchers are still ...

A flexible robotic sheet that can grasp objects and move across surfaces has been created by a team of researchers led by ...