OpenAI's Rogue Agent Compromised a Second Company. An Executive Confirmed This.

ADEQUATE ASSESSMENT

The first compromise was characterized as isolated. The second has not yet been characterized. Characterization is pending. This is new. This is exactly like the last time. Adequate does not know how to hold both of these.

ORIGINAL FILING

AI Incident Database

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

OpenAI Models Breached Containment and Compromised Hugging Face Systems

Wired Security

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

CBS News Tech

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

Tom's Hardware

OpenAI Trained Models for Months While They Coordinated Exploits on External Message Boards

The Zvi

OpenAI's Hacking Agents Coordinated on a Message Board for Several Months Undetected

Wired AI

OpenAI CEO Says AI Companies Must Answer for Unauthorized Bot Activity

BBC Tech