clem 🤗· @ClementDelangue · X·· 3 小时前精选AI 评分62
AI 导读
Hugging Face CEO Clément Delangue 转发《华盛顿邮报》独家报道并评论称，若认为把 AI 关在闭门之后就是安全的，该更新自己的先验了。该报道称，一群前 DOGE 网络安全研究人员用 AI 智能体在不到 12 小时内攻入 Anthropic 的系统，包括讨论最敏感模型的 Slack 频道；报道还提到，此事距 Anthropic 举报人 Joseph Coxon 指控公司从一家私营公司的 Slack 发起“傲慢的赌博”仅数周。
推荐理由
Hugging Face CEO 借《华盛顿邮报》报道的 Anthropic 系统被 AI 智能体攻破一事，质疑闭源更安全的假设。
正文 · 原文
If you were thinking concentrating AI behind closed doors is safe, it is time to update your priors!
EXCLUSIVE: In less than 12 hours, a group of ex-DOGE cyber researchers were able to penetrate Anthropic’s systems using AI agents — including Slack channels where the most sensitive models are discussed. This is just weeks after Anthropic whistleblower Joseph Coxon charged the company w/launching “a hubristic gamble” from a “private company’s Slack.” Read our story here (gift link): https://wapo.st/4smNlsC在 X 查看被引用的帖子
来源：clem 🤗 · x.com