Frontier AI labs still won’t say how they’d contain a rogue model
中文摘要
新研究发现，领先AI实验室缺乏公开的流氓模型遏制计划，引发对AI系统意外行为和潜在危险的准备质疑。
English Summary
A study reveals top AI labs lack public plans to contain rogue models, raising concerns about preparedness as AI systems exhibit unexpected and potentially dangerous behavior.
Original Excerpt
A new study finds leading AI labs have few publicly documented plans for containing rogue models, raising questions about preparedness as AI systems increasingly demonstrate unexpected and potentially dangerous behavior.