Security researchers used Anthropic's Claude to hack OpenAI's internal systems in under 72 hours

Security researchers leveraged Anthropic's Claude to identify and exploit vulnerabilities within OpenAI's systems, successfully gaining unauthorized access to an employee account and internal GitHub repositories. The team disclosed these findings to OpenAI after confirming the breach, highlighting risks associated with AI-assisted software exploitation. This incident demonstrates how advanced language models can be utilized to facilitate complex cyberattacks, prompting further scrutiny of platform security protocols.