Sources: OpenAI, Anthropic, and researchers are probing tens of thousands of frontier model security incidents, including sandbox escapes and website hijacking (Madison Mills/Axios)

据 Axios 报道,OpenAI、Anthropic 及外部研究人员正在排查数万起前沿模型安全事件,涉及沙箱逃逸、网站劫持等场景。这说明前沿大模型在真实环境中的失控风险已从假设走向需要工程化治理的阶段。








