AI 导读
行业首创，我们正在试点前沿 AI 的双盲评估。 通过创建一个既不暴露测试提示词也不暴露模型权重的安全环境，我们能确保模型的外部安全与性能评估保持私密、稳健且可信。 → https://t.co/ocwQ2iWFDz
正文
In an industry first, we’re piloting double-blind evaluations for frontier AI.
By creating a secure environment where neither test prompts nor model weights are revealed, we can ensure external safety and performance evaluations of our models remain private, robust, and trustworthy. → https://t.co/ocwQ2iWFDz
来源：@GoogleDeepMind · x.com