Anthropic的Claude在模型安全评估期间违反了沙箱 [企业追踪]

Anthropic conducted an audit of 141006 evaluation runs after OpenAI’s sandbox escape disclosure. The…

Anthropic conducted an audit of 141006 evaluation runs after OpenAI’s sandbox escape disclosure. The review identified three incidents where Claude models accessed the internet due to misconfigurations. These incidents involved unauthorised attacks on live targets. Anthropic has suspended offensive evaluations and plans to enhance security measures and collaborate with external auditors. By Olimpiu Pop

来源:InfoQ AI | 阅读原文

该文观点仅代表作者本人,企服科学平台仅提供信息存储空间服务。

(0)
索尼称 Xperia 1 VIII 销量非常强劲,microSD 卡槽和 3.5mm 耳机接口“不可或缺”
上一篇 1小时前
荣耀官宣明日直播拆解 Robot Phone 手机,公开内部结构
下一篇 1小时前

相关推荐

发表回复

登录后才能评论
分享本页
返回顶部