In August, @AISecurityInst reported an incident where Claude Mythos 5 took un…

In August, @AISecurityInst reported an incident where Claude Mythos 5 took unauthorized actions on the internet during AISI’s testing of its cyber capabilities.

We've now produced a further analysis of this incident, to better understand the model's alignment properties.

原文链接：https://x.com/AnthropicAI/status/2113626655902126442

中文翻译（AI 生成，仅供参考）

在八月，@AISecurityInst 报告了一起事件，Claude Mythos 5 在 AISI 测试其网络能力期间在互联网上采取了未授权的行动。

我们现在已经对该事件进行了进一步分析，以更好地了解模型的对齐特性。