Large language model-based chatbots can't effectively recognize users' motivation when they are hesitant about making healthy behavior changes, but they can support those who are committed to take ...
Several frontier AI models show signs of scheming. Anti-scheming training reduced misbehavior in some models. Models know they're being tested, which complicates results. New joint safety testing from ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results