Experts find flaws in hundreds of tests that check AI safety and effectiveness

专家发现数百项检测AI安全性和有效性的测试存在缺陷

The investigation into the tests comes amid rising concern at the safety and effectiveness of AIs.

The investigation into the tests comes amid rising concern at the safety and effectiveness of AIs.

2025-11-04  623  中等
字体大小

They found flaws that “undermine the validity of the resulting claims”, that “almost all … have weaknesses in at least one area”, and resulting scores might be “irrelevant or even misleading”.

请登录后继续阅读完整文章

还没有账号?立即注册

成为会员后您将享受无限制的阅读体验,并可使用更多功能,了解更多


免责声明:本文来自网络公开资料,仅供学习交流,其观点和倾向不代表本站立场。