We partnered with @fmf_org and its member firms on a new framework to help identify when bypassing an AI system's safeguards could enable serious cyber harm, and prioritize stronger protections.

"...This framework is an important step toward a common methodology for evaluating

原文链接:https://x.com/OpenAI/status/2118795218099253606

中文翻译(AI 生成,仅供参考)

我们与 @fmf_org 及其成员公司合作,制定了一个新框架,以帮助识别何时绕过 AI 系统的防护措施可能导致严重的网络危害,并优先考虑更强的保护措施。

……该框架是朝着建立统一评估方法迈出的重要一步。