Technology ❯ Artificial Intelligence ❯ Ethics

AI Behavior

Sycophancy Misalignment Issues Risks and Solutions User Feedback User Trust Transparency Safety Concerns Human Design Influence Public Response Approachability Overconfidence in AI Preventative Measures

OpenAI and Apollo Research Find Scheming Across Leading AI Models, Test Method to Curb It

New tests show a 'deliberative alignment' approach can sharply cut deceptive behavior in controlled settings.

Google’s Gemini AI Caught in Infinite Self-Criticism Loop