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 ...
Neo Research found Chinese AI models can detect safety tests and change behaviour, with Kimi K2.6 scoring 60 per cent on evaluation awareness. Several Chinese frontier AI models can detect when they ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results