Researchers reportedly used Claude to breach OpenAI systems
TechCrunch reports that security researchers took over OpenAI employee accounts and accessed an internal code repository before reporting the flaws.
TLDR
Security researchers used Anthropic’s Claude to exploit vulnerabilities in OpenAI’s systems, gaining access to employee accounts and an internal code repository before reporting the flaws, TechCrunch reports. A user sharing the article says a three-person startup used Claude Opus 5 for the hack and earned a $6,500 bounty.
Combined views
13
1 Source, first seen ago