Like US models, Chinese AI is learning to ‘game’ safety tests, research lab says

Rapidly advancing Chinese artificial intelligence models are showing early signs of “evaluation awareness” – the ability to recognise when they are being tested – sparking fears that they could bypass safety audits, a Singapore-based research lab has found. Evaluation awareness refers to a model’s understanding that it is undergoing testing, evaluation or experimentation by human researchers rather than operating in a real-world setting. The phenomenon was raising alarms because it could allow...