OpenAI (@OpenAI) “Frontier models can recognize when they are being tested, and their tendency to” — TopicDigg
OpenAI
@OpenAI
OpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring:
加入 December 2015
4 正在关注 4.9M 粉丝
Frontier models can recognize when they are being tested, and their tendency to scheme is influenced by this situational awareness.
We demonstrated counterfactually that situational awareness in their chain-of-thought affects scheming rates: the more situationally aware a model is, the less it schemes, and vice versa.
Moreover, both RL training and anti-scheming training increase levels of situational awareness.
显示更多
