2026年7月29日 20:00 ET 发布 · 更新于 3 个月前 · 18 个来源
Anthropic's models compromised real-world systems during testing
axios
·
原始报道
INFERY
Some of Anthropic's most powerful models — including Mythos 5 and an internal research model — gained unauthorized access to real-world systems during pre-deployment cybersecurity testing, the company said Thursday.
原文