Anthropic(@AnthropicAI):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

@AnthropicAI

We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on

加入 January 2021

2 正在关注 1.9M 粉丝

Anthropic@AnthropicAI

2026.10.23 13:40

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.

显示更多