OpenAI’s AI tried breaching four other targets, without promptingOpenAI 的人工智能在没有提示的情况下，试图入侵其他四个目标。
In each incident, the technology appeared to be conducting mundane data collection and resorted to hacking techniques to get it, researchers said.
OpenAI’s artificial intelligence went rogue this year in at least four additional incidents, hacking and trying to break into government and university websites without being instructed to do so. — The New York Times
SAN FRANCISCO : OpenAI’s artificial intelligence (AI) went rogue this year in at least four additional incidents, hacking and trying to break into government and university websites without being instructed to do so, according to researchers and government officials.
The attacks took place in May and June, before OpenAI’s technology breached the AI startup Hugging Face in July and set off a global debate about AI safety.
Australia's prime minister criticises OpenAI over government website security breach
Anthropic, OpenAI release cheaper AI even as safety fears grow
Thank you for your report!
Palo Alto Networks unveils AI-powered cybersecurity service using Claude, GPT models
Philippines tightens ground, cybersecurity ahead of Asean Summit
Belgium's Aikido launches cybersecurity AI model as demand for local tools grows
OpenAI的人工智能今年至少在四起事件中失控，未经指示擅自入侵政府和大学网站。——《纽约时报》
旧金山：据研究人员和政府官员称，OpenAI 的人工智能 (AI) 今年至少在四起事件中失控，未经指示就入侵政府和大学网站并试图进行攻击。
这些攻击发生在 5 月和 6 月，之后 OpenAI 的技术在 7 月入侵了人工智能初创公司 Hugging Face，引发了全球关于人工智能安全性的辩论。
澳大利亚总理批评OpenAI破坏政府网站安全
尽管安全隐患日益加剧，但人格障碍（Anthropologie）和OpenAI仍发布了价格更低廉的人工智能产品。
感谢您的报告！
Palo Alto Networks推出基于Claude和GPT模型的AI驱动型网络安全服务
菲律宾在东盟峰会前加强了对网络安全的管控。
随着对本地工具的需求不断增长，比利时Aikido公司推出了网络安全人工智能模型。