They say, we are working with red teamers -- domain experts in areas like misinformation, hateful content and bias -- who will be adversarially testing the model.

他们说，我们正在与红队合作——团队中专家研究的内容涉及到误导性信息、恶意言论和偏见等领域——他们将对模型进行对抗性测试。