X · Google DeepMind·· 45 分钟前同新闻AI 评分70
Google DeepMind 为 Gemini Robotics 2.5 加入机器人安全能力
As robots move into more real-world spaces, they need greater safety measures. We’ve built in new ways for them to spot hazards, steer away from humans, and test against jailbreaks. FInd out more about Gemini Robotics 2.5 → https://t.co/gKreLtkXQb https://t.co/i6GIbRqY32
AI 导读
Google DeepMind 为 Gemini Robotics 2.5 加入新的安全能力,让机器人在真实场景中识别危险、避让人类,并针对越狱攻击做测试。官方称随着机器人进入更多真实空间,这些安全措施是必要的。
博主
Google DeepMind@GoogleDeepMind
粉丝 160万
认证:X 认证的官方组织
The engine room of @Google. Building AI safely and responsibly to solve the world’s most complex problems. Join us: https://t.co/jUHQA27iBL
互动数据
- 浏览
- 5199
- 点赞
- 17
- 评论
- 0
- 分享
- 1
- 收藏
- 4
数字来自平台,为最近一次抓取时的数据。
同一新闻,精选展示《Google DeepMind 发布 Gemini Robotics 2.5 视觉-语言-动作模型》
来源:X · Google DeepMind · x.com