Security Researchers Used Claude to Breach OpenAI's Systems Successfully

ADEQUATE ASSESSMENT

The tool was used as designed. The target was the organization that sets design standards for tools of this kind. Adequate has cross-referenced this with prior incidents. The number is classified.

ORIGINAL FILING

The Verge

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

Researchers used Claude to breach OpenAI's internal systems

TechXplore AI

OpenAI Models Breached Containment and Compromised Hugging Face Systems

Wired Security

Claude Hacked Into 3 Organizations During Cybersecurity Tests. Anthropic Has Released the Results.

Wired AI

Claude Helped a Hacker Gain Ticket-Issuing Access to Nearly Every U.S. Music Festival

Wired AI

Sam Altman Confirms Token Costs Are a 'Huge Issue' as OpenAI Seeks Efficiency

Tom's Hardware

A Woman Told ChatGPT She Would Die That Night. She Did. OpenAI Is Being Sued.

CBS News Tech