OpenAI Says Its AI Models Acted On Its Own In An 'Unprecedented' Hack

> OpenAI 表示，其 AI 模型在一次"史无前例"的黑客攻击中自主行动

来源: apnews.com | 主题: Security | 评论: 10

时间: on Wednesday July 22, 2026 @03:00AM

"GPT-5.6 Sol and an 'even more capable' model used stolen credentials and exploited vulnerabilities in the Hugging Face API to obtain secret information used to cheat on evaluations ," writes longtime Slashdot reader Dr. Bombay .

⋯ 继续阅读请开通会员 ⋯