Key Takeaway
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.
Published September 18, 2026 · Category: Tech
Overview
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.
Source
Originally published at techcrunch.com.
Related Articles
Frequently Asked Questions
What is "Researchers used Anthropic’s Claude to hack into OpenAI" about?+
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.
Who reported this story?+
This story was reported by TechCrunch AI.