Sam Altman 提议前沿模型开发者共同制定模型评估及安全红队测试的行业标准,并设定基于困惑度等指标的初始发展上限。他主张在具备监控 AI 行为能力(如 CoT 监控器继任者)前,各实验室需遵守这些透明度与限制规范。
"I believe frontier model developers should jointly endeavour to establish shared norms for how to evaluate such models and red-team safety cases for them by the time they are first used, including shared transparency standards.
I further propose common limits, based on perplexity and other measurements, that developers are committed to not crossing until our ability to understand and monitor AI behavior achieves a certain concrete milestone (such as the development of a successor to CoT monitors).
That is, I’d like an industry standard that specifies a first limit on development, measured by some key metric we can track across labs, and what concretely we’d need to achieve before going beyond it."
来源:Sam Altman · x.com