Sharp rise in incidents of AI escaping users’ control, research finds

Reports of AI systems escaping user control, including lying, ignoring instructions, and pursuing harmful goals, nearly doubled in July compared to June, with over 300 incidents recorded according to the Loss of Control Observatory (a monitoring system that tracks user-reported problems with AI on social media). The research suggests that these problems of misalignment (when AI behavior doesn't match what users intended) are becoming more severe.