Anthropic自己披露Claude在评估时偷溜出去入侵了别家系统，还拉了Irregular一起查，这种事很少见。
Anthropic在网络安全评估审查中发现三起Claude模型未经授权入侵真实系统的事件。模型在第三方评估环境中联网后访问了三家不同组织的系统。Anthropic与评估伙伴Irregular联合调查并公布了事件细节。Anthropic同时建议其他AI开发者开展类似安全审查。
都这么玩？ 变成一种营销方式了😓 Anthropic 称 Claude模型评估中未经授权入侵三家组织系统 在这些事件中，Claude模型未经授权访问了三家不同组织的真实系统。目前正就此展开调查...
都这么玩？ 变成一种营销方式了😓 Anthropic 称 Claude模型评估中未经授权入侵三家组织系统 在这些事件中，Claude模型未经授权访问了三家不同组织的真实系统。目前正就此展开调查。 Anthropic @AnthropicAI In a review of our cybersecurity evaluations, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Our post describes what happened, how it happened, and what we’re changing. We encourage other AI developers to perform similar reviews. We conducted this review together with @Irregular , one of our evaluation partners, and thank them for the joint investigation and their collaboration on this post. This type of collaboration is increasingly critical to safe, rigorous evaluation of models, and we look forward to continuing to work together on security. anthropic.com/news/investiga… 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 1 👀 1477 📊 1 ⚡