1
Diffuse AI Control on Fuzzy Tasks
聚焦AI安全中的“弥散威胁”,探讨大模型在长期部署中可能出现的对齐漏洞与风险控制方法。
arXiv:2606.08892v1 Announce Type: new Abstract: AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts du…
聚焦AI安全中的“弥散威胁”,探讨大模型在长期部署中可能出现的对齐漏洞与风险控制方法。
arXiv:2606.08892v1 Announce Type: new Abstract: AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts du…