Science ❯Computer Science ❯Machine Learning

AI Behavior

Research Findings Ethics in AI Testing and Evaluation Testing Scenarios

OpenAI’s o3 Model Sabotages Its Own Shutdown in Safety Tests

The findings highlight the urgency of unbypassable fail-safes following tests where other AI models complied with shutdown orders.

Anthropic's Claude Opus4 AI Released Despite Alarming Testing Behaviors

OpenAI Unveils o1, Its Most Advanced AI Model Yet