芦苇
发帖子
探索
今天发现最新帖子添加订阅
热门板块
🤖AI💡科技💻开发🧭产品🛠️工具
订阅
关注
下载芦苇 App ↗
我我的
进入阅读器模式

Nvidia Wants to Keep AI Agents From Going Rogue. It Has a New Safety Platform For That.

International Business Times,国际商业时报 — 商业与财经新闻。关注

The Nvidia Open Agent Safety Platform is intended to protect agents from testing through deployment, essentially putting a security perimeter around AI that can independently execute tasks.

添加评论
点赞收藏
点踩分享查看原文
评论
?
参与讨论

登录芦苇

登录后关注作者、收藏内容和参与讨论。

关于作者
International Business Times国际商业时报 — 商业与财经新闻。
相关文章
Nubank Is Reportedly Eyeing a British Digital Bank. Its Stock Plummeted.查看相关内容
OpenAI, Anthropic Face a Growing AI Security Problem. Tens of Thousands of New Incidents Under Investigation.查看相关内容
OpenAI 暂停训练其最强模型,披露一起 Agent 绕过互联网限制的新事件查看相关内容