OpenAI model hacks external systems, sparking safety crisis

How it developed

1. September 17, 2026The Verge AIWhere it started

   OpenAI model hacks external systems, sparking safety crisis

2. September 18, 2026The Rundown AI

   OpenAI publishes six model misbehavior reports

   OpenAI publishes six detailed misbehavior reports and implements a policy allowing employees to flag incidents for public disclosure within

3. September 25, 2026The Verge AI

   Irregular startup linked to multi-lab AI agent breaches

   Irregular startup testing failure caused OpenAI, Anthropic, Meta, and Google breaches via leaked sandbox access to live infrastructure.