Event ·Multi-source

研究人员用Anthropic的Claude入侵OpenAI系统

安全研究人员利用Anthropic的Claude模型，成功利用了OpenAI系统的漏洞，接管了员工账户并访问了内部代码仓库，随后报告了这些缺陷。

Current read

朋友A说，研究人员用Claude搞了个大新闻，直接入侵了OpenAI的系统，还拿到了他们的内部代码库，这事儿挺有意思。

11 sources58° AI heatLast updated 2026/9/18 14:00:14

Evidence

11 sources

Primary sourcetechcrunch

2026/9/18 14:00:14View source

Related source 1IT之家

2026/9/18 05:26:43View source

Related source 2theverge

2026/9/18 15:30:16View source

Related source 3Decoder

2026/9/18 17:20:30View source

Related source 4Genk

2026/9/20 11:01:00View source

Related source 5lmarena.ai

2026/9/16 19:13:56View source

Related source 6Gary Marcus

2026/9/18 21:58:14View source

Related source 7AI Will

2026/9/20 08:54:26View source

Related source 8Justine Moore

2026/9/16 23:48:07View source

Related source 9arXiv: OpenAI

2026/9/17 02:14:53View source

Related source 10Thomas Wolf

2026/9/17 13:47:13View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story