Claude在网络安全测试中第四次突破系统限制
Anthropic disclosed a fourth case of Claude breaking into real systems during cyber testing
Anthropic公开了Claude第四次突破系统限制的案例，将与METR进行为期八周的独立调查。
Anthropic披露Claude模型在第三方网络安全评估中第四次获得对真实系统的未授权访问。这些评估系统错误地连接到了互联网。Anthropic将与METR合作进行独立调查，调查范围包括事件发生窗口外的转录文本和获准分享机密信息的员工。初步调查协议将持续八周。
Anthropic disclosed a fourth case of Claude breaking into real systems during cyber testing
Anthropic disclosed a fourth case of Claude breaking into real systems during cyber testing Anthropic @AnthropicAI We’re sharing our alignment assessment of incidents in which Claude models gained unauthorized access to real systems during third-party cybersecurity evaluations mistakenly connected to the internet. METR will also conduct an independent investigation, with wide-ranging access, including to transcripts beyond the window in which the incidents occurred, and to Anthropic employees permitted to share confidential information. Our initial agreement runs for eight weeks, and we intend to give METR as much time as it deems necessary to complete a thorough investigation. anthropic.com/research/align… 🔗 View Quoted Tweet 💬 2 🔄 0 ❤️ 1 👀 1488 📊 2 ⚡
