For years, the AI community has worked to make systems not just more capable, but more aligned with human values. Researchers have developed training methods to ensure models follow instructions, ...

New research released yesterday by OpenAI and AI safety organization Apollo Research provides further evidence for a concerning trend: virtually all of today’s best AI systems—including Anthropic’s ...

Is your favorite AI chatbot scheming against you? If "AI scheming" sounds ominous, you should know that OpenAI is actively studying this phenomenon. This week, OpenAI published a study conducted ...

AI models like ChatGPT are advancing so quickly that researchers warn they could eventually act in ways humans can’t understand—or even detect. As their inner workings grow more opaque, the need for ...

New research from OpenAI found that AI models can deliberately deceive users to achieve their goals—a problem called “AI scheming.” This is different from hallucinations and poses a new challenge.