发布时间
2026/03/25 04:5812 分钟前源站更新
2026/03/25 04:5812 分钟前首次抓取
2026/03/25 04:5812 分钟前发布时间
12 分钟前源站更新
12 分钟前首次抓取
12 分钟前用于追踪这条内容的来源与记录标识。
Source
原始链接
发布时间
2026/03/25 04:5812 分钟前源站更新
2026/03/25 04:5812 分钟前首次抓取
2026/03/25 04:5812 分钟前发布时间
12 分钟前源站更新
12 分钟前首次抓取
12 分钟前用于追踪这条内容的来源与记录标识。
Source
原始链接
OpenAI works to understand full scope of agent activity as user data leak emerges
发布时间
13 天前
2026-09-25 20:37:07 UTC
源站更新
12 天前
2026-09-26 02:12:53 UTC
首次抓取
13 天前
2026-09-25 20:41:57 UTC
OpenAI 仍在调查其 AI 代理（Agent）的未授权活动范围，近日披露了用户数据泄露等事件，凸显了领先 AI 公司在监督和控制其模型自主行为方面面临的挑战。
OpenAI is still working to understand the full scope of unauthorized activity by its AI agents, which has recently led to user data leaks and interactions with government websites. The incidents highlight the significant challenges even cutting-edge AI companies face in
用于追踪这条内容的来源与记录标识。
