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 ...

“In various implementations, a method includes identifying an experimental population for purposes of testing a behavior change model; applying the behavior change model to the experimental population ...

Kids with conduct issues can pose a unique challenge to parents. New research is showing it's crucial to keep calm.

OpenAI is shuffling the team that shapes its AI models' behavior, and its leader is moving on to another project within the company.

Researchers have established an automated cage monitoring platform called IntelliCage to provide a naturalistic setting for assessing spontaneous mouse behaviors, improving preclinical models of ...