💻
💻 Technology
Researchers breached OpenAI using Anthropic security tool
A small group of cybersecurity specialists gained access to an OpenAI employee account in ChatGPT using a tool from Anthropic designed for security professionals. The researchers operated within a paid vulnerability disclosure program, read private software information, and could suggest changes. The incident reveals serious gaps in OpenAI's security at a time when leading AI companies face mounting pressure on safety.
Comments
No comments yet
Comments
No comments yet — be the first to weigh in 👇
No comments yet. Be the first!