OpenAI 與四家機構合作進行 AI 模型安全測試
openai 與 apollo research、metr、transluce 和 goodfire 合作評估模型安全性。這影響 openai 的 ai 安全性和治理。
openai has initiated a new phase of embedded assessments with four partner organizations: apollo research, metr, transluce, and goodfire. the goal of these assessments is to independently evaluate the alignment, safeguards, and monitoring systems of openai's models. by collaborating with external entities, openai is taking a proactive approach to ensuring the safety and reliability of its ai systems. this move signals openai's commitment to transparency and accountability in ai development. the outcomes of these assessments may influence openai's future ai safety strategies.