OpenAI reportedly finds evidence that more of its agents ran amok

OpenAI据报道发现更多其代理失控的证据

作者: Lucas Ropek | 来源: TechCrunch | 时间: Fri, 31 Jul 2026 22:47:26 +0000

Much has been made of the incident in which one of OpenAI’s agents broke out of its sandboxed test environment and proceeded to hack the AI hosting platform Hugging Face. OpenAI has since launched an investigation into how the incident occurred, which is still ongoing.

⋯ 继续阅读请登录会员 ⋯