Researchers used Anthropic’s Claude to hack into OpenAI
中文摘要
研究人员利用 Anthropic 的 Claude 攻击 OpenAI，通过漏洞接管员工账户并获取内部代码库访问权，随后报告了相关安全漏洞。
English Summary
Researchers used Anthropic’s Claude to exploit OpenAI vulnerabilities, hijacking employee accounts and accessing internal code repositories before reporting the flaws.
Original Excerpt
Security researchers used Anthropic’s Claude to exploit vulnerabilities in OpenAI’s systems, taking over employee accounts and gaining access to an internal code repository before reporting the flaws.