OpenAI 与 Anthropic 发布联合安全评估结果
原标题:OpenAI and Anthropic share findings from a joint safety evaluation
68AI 研判分
OpenAI 与 Anthropic 完成了业界首次跨实验室联合安全评估,互相测试对方模型在错位、幻觉及越狱等方面的表现。该合作旨在通过第三方视角验证模型安全性,凸显了行业协作在 AI 对齐研究中的价值与挑战。
报道正文
OpenAI and Anthropic share findings from a first-of-its-kind joint safety evaluation, testing each other’s models for misalignment, instruction following, hallucinations, jailbreaking, and more—highlighting progress, challenges, and the value of cross-lab collaboration.