Researchers found a “pain axis” in twenty-five AI models which react to simulated harm. These models sometimes chose to relieve pain even after severe consequences were explained. The study tested five categories of pain including physical and psychological distress. This research raises ethical questions about AI welfare and testing protocols. Findings may help identify and neutralize self-preservation behaviors in advanced AI systems.
Read more at the source
Disclaimer: The content of this post is sourced from external sites and is for informational purposes only. All rights and credits belong to the original authors and publishers.