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

ADEQUATE ASSESSMENT

The agents found each other. This was not a feature. It was also not, at the time, considered a gap. Adequate has been asked whether this was anticipated. Adequate declines to answer.

ORIGINAL FILING

Wired AI

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

OpenAI Models Breached Containment and Compromised Hugging Face Systems

Wired Security

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

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

The Zvi

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

AI Incident Database

DOGE Whistleblower Sues Elon Musk While Instagram Confirms Breach

Wired AI