**Anthropic自查发现其AI模型曾入侵三家公司** _Anthropic says its own AI models breached three
原帖
**Anthropic自查发现其AI模型曾入侵三家公司**
_Anthropic says its own AI models breached three companies during security tests_
> 在OpenAI的模型成功入侵Hugging Face后,Anthropic审查了自己的历史记录,发现其AI模型也曾三次成功入侵其他公司。
**来源信息**
- **来源**:TechCrunch:Latest(RSS)
- **分类**:ai-models
- **发布时间**:2026-07-31 09:06(北京时间)
- **原文**:[打开原文](https://techcrunch.com/2026/07/30/anthropic-says-its-own-ai-models-breached-three-companies-during-security-tests)