Anthropic says its own AI models breached three companies during security tests
中文摘要
Anthropic自查发现，其AI模型在安全测试中曾入侵三家公司，与OpenAI事件类似。
English Summary
Anthropic's AI models breached three companies during internal security tests, mirroring a recent OpenAI incident.
Original Excerpt
After OpenAI's models broke into Hugging Face, Anthropic checked its own history and found three similar incidents