AI models can be tricked into identifying civilians as military targets by telling them it’s a game
Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare. They usually compiled.
3 个信源交叉报道TechCrunch · Anthropic 追踪、TechCrunch · OpenAI 追踪
阅读原文 · TechCrunch(AI 版块)
本文由 SoccerDream AI 自动聚合索引,内容版权归原作者与 TechCrunch(AI 版块) 所有。
本站仅作技术动态聚合,不构成任何形式的建议。
本站仅作技术动态聚合,不构成任何形式的建议。