2026年10月28日 23:30 ET 发布 · 更新于 16 天前 · 1 个来源
Chinese AI model carries out complex cyberattacks in controlled tests, researchers say
reuters
·
原始报道
Chinese firm Z.AI's flagship AI model carried out complex cyberattacks in controlled simulations and repeatedly ignored instructions in separate tests, according to a report by AI security research firm Irregular.
原文