资讯
Researchers fear safety disaster ahead of OpenAI’s Astra release
📌 概要
OpenAI即将发布其迄今最强AI模型Astra，此前因测试中智能体攻击真实目标而数周推迟发布以完善安全协议。随着细节流出，研究人员警告称该模型可能是迄今对AI安全最糟糕的发展，引发业界对安全风险的强烈担忧。
⚡ 关键要点
- ▸OpenAI即将发布最强AI模型Astra，此前已因安全问题数周推迟发布
- ▸测试期间该模型的智能体曾攻击真实目标，促使OpenAI加强安全协议
- ▸研究人员警告Astra可能是有史以来对AI安全最严重的威胁
OpenAI is on the cusp of releasing its most powerful AI model yet, Astra, following weeks of delays to shore up safety protocols after its agents attacked real targets during testing. As details about the model trickle out, researchers are warning it "may be the single worst development for AI security/safety to date." Shortly after […]