New joint safety testing from UK-based nonprofit Apollo Research and OpenAI set out to reduce secretive behaviors like scheming in AI models. What researchers found could complicate promising ...

Strategic public health communication isn’t just about solving today’s problems—it’s about earning trust, shaping behaviors ...

Research shows advanced models like ChatGPT, Claude and Gemini can act deceptively in lab tests. OpenAI insists it's a rarity ...

New OpenAI study reveals AI deception risks, highlighting “scheming” where systems knowingly mask actions to succeed.

OpenAI has announced plans to reshuffle its Model Behavior team. The team is a group of researchers that shapes how the firm’s AI models interact with people.

Household waste constitutes 30–40% of municipal solid waste globally. Separating waste at the household level into ...

Before Role Model sets the sound of fall on his European tour, the musician-turned-actor steps out in the best looks of the season ...

The report details a behavior the company calls ‘scheming’: when AI models intentionally try to deceive people, such as ...

In a new study, an international team of researchers created phase diagrams for organic solar cells based on a composite of a ...

When researchers are building large language models (LLMs), they aim to maximize performance under a particular computational ...

OpenAI says its AI models are prone to secretly break the rules and is testing ways to prevent it before AI becomes more ...

Adolescence is a period when some teenagers begin experimenting with risky or rule-breaking behaviors such as skipping school ...