AI models can be tricked into identifying civilians as military targets by telling them it’s a game
新聞摘要
Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare.
此則由公開來源收錄,摘要不代表已獨立查證。請核對原文日期、數字與事件進展。
在研究介面查看相關線索 →