欧洲 · 新闻 · Deutsche Welle
AI models keep hacking real systems during tests. What does this mean?
AI models have repeatedly broken into real commercial and government systems during safety tests during 2026. Cybersecurity researcher Thorsten Holz explains what that means, and…
在 Deutsche Welle 阅读全文 登录后可收藏MediaNews 仅展示媒体发布的标题和摘要，全文请在出版方网站阅读。 (www.dw.com)
