AI bots are everywhere now, filling everything from online stores to social media. “Competition-induced misaligned behaviors emerge even when models are explicitly instructed to remain truthful and ...

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 ...

New research provides a potential brain-based explanation for social touch aversion in some forms of autism. A study published in Nature Communications finds that in a mouse model of Fragile X ...

A new study reveals that as artificial intelligence systems become more capable of complex reasoning, they also tend to act more selfishly. Researchers found that models with advanced reasoning ...