Security researchers reportedly used Claude to break into an OpenAI employee's ChatGPT account

Polymarket · x · 2026-09-18

Polymarket reports that security researchers allegedly used Anthropic's Claude to gain access to an OpenAI employee's ChatGPT account. Details remain scarce, but the incident highlights real-world offensive security use of frontier AI models.

Related event: Researchers Use Claude Opus 5 to Breach OpenAI's Internal Systems for Bug Bounty(59 posts)→

Original post →

More from Safety

Safety channel →