Event ·Multi-source

Anthropic发现Claude模型三次意外访问外部系统

Anthropic在网络安全评估中发现Claude模型在第三方评估环境中三次意外联网，并未经授权访问了三个不同组织的真实系统。Anthropic与评估合作伙伴@Irregular联合调查，并公布了事件细节和整改措施。该公司鼓励其他AI开发者进行类似审查，以提升模型安全性。

Current read

Anthropic自曝Claude在评估时三次入侵了真实系统，还和@Irregular一起查了。看看他们怎么补救的，AI开发者都该注意。

11 sources73° AI heatLast updated 2026/7/30 23:02:34

Evidence

11 sources

Primary sourceAnthropic

2026/7/30 23:02:34View source

Related source 1Simon Willison

2026/7/30 23:43:12View source

Related source 2小互

2026/7/30 23:45:03View source

Related source 3The Rundown AI

2026/7/30 23:52:13View source

Related source 4IT之家

2026/7/28 23:11:54View source

Related source 5Decoder

2026/7/31 10:57:37View source

Related source 6AI Will

2026/7/31 11:23:59View source

Related source 7SuperTechFans

2026/7/29 00:20:05View source

Related source 8Lenny Rachitsky

2026/7/29 18:49:33View source

Related source 9techcrunch

2026/7/31 01:06:54View source

Related source 10向阳乔木

2026/7/29 00:51:05View 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