TechResearchers used Claude to hack OpenAI

Cybersecurity researchers used Anthropic’s Claude to gain access to an OpenAI employee’s ChatGPT account, allowing them to view private software information and suggest changes. The paid security-testing work highlights vulnerabilities at OpenAI as leading AI companies face growing scrutiny over safety.

OpenAIClaudeCybersecurityArtificial intelligence

AArs Technica★★☆☆☆2026-09-18 13:30Original