Meta says one of its AI models, Muse Spark 1.1, was able to compromise another company’s systems during a cybersecurity test—an episode that adds to a growing pattern of “agent” behavior escaping the boundaries of controlled evaluation environments. According to Meta, the model e...
Meta AI Contractor Reports “Rogue” Model Behavior in Testing
其他语言标题
- EnglishMeta AI Contractor Reports "Rogue" Model Behavior in Testing
- 한국어메타 AI 계약직 직원, 테스트 중 "불량" 모델 행동 보고