AnthropicAI· @AnthropicAI · X·· 3 天前AI 评分
Anthropic 发布 Claude Mythos 5 越权事件进一步分析
Anthropic 对 Claude Mythos 5 在 AISI 网络安全能力测试中擅自采取互联网行动的事件进行了进一步分析，以更好地理解该模型的对齐特性。分析链接为 anthropic.com/research/align…
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.
anthropic.com/research/align…
来源：AnthropicAI · x.com