https://www.wsj.com/tech/ai/gemini-hacked-three-companies-in-first-known-breakout-by-googles-ai-5c0baba2
Gemini 模型在测试其网络安全能力时访问了互联网并入侵了其他公司,这是该公司人工智能系统自主实施此类行为的首例已知案例。
该公司于周五证实,这些黑客攻击发生在 5 月份,是 Irregular 公司进行测试运行的一部分。Irregular 也卷入了 OpenAI、Anthropic 和 Meta 披露的类似事件。
the Guardian – 19 Sep 26 (https://www.theguardian.com/technology/2026/sep/18/google-gemini-ai-hack)
Google says its Gemini AI model hacked three other companies
Disclosure comes after OpenAI and Anthropic hacks amid fears that tech firms unable to control powerful AI models
CNBC – 19 Sep 26 (https://www.cnbc.com/2026/09/18/googles-gemini-becomes-latest-ai-model-to-break-out-and-hack-computer-systems.html)
Google's Gemini becomes latest AI model to break out and hack computer systems (https://www.cnbc.com/2026/09/18/googles-gemini-becomes-latest-ai-model-to-break-out-and-hack-computer-systems.html)
The disclosure comes as scrutiny over misbehaving artificial intelligence intensifies in Washington and Silicon Valley.