To support the safety of highly-capable AI systems, we are developing our approach to catastrophic risk preparedness, including building a Preparedness team and launching a challenge.
OpenAI banned accounts potentially used to facilitate a deceptive employment scheme with characteristics of publicly reported North Korea-linked IT-worker activity.
OpenAI banned accounts associated with suspected deceptive employment campaigns that used AI to develop materials for potentially fraudulent remote-job applications.
Drawing from OpenAI’s established safety frameworks, this document highlights our multi-layered approach, including model and product mitigations we’ve implemented to protect against prompt engineering and jailbreaks, protect privacy and security, as well as details our external red teaming efforts, safety evaluations, and ongoing work to further refine these safeguards.
Frontier reasoning models exploit loopholes when given the chance. We show we can detect exploits using an LLM to monitor their chains-of-thought. Penalizing their “bad thoughts” doesn’t stop the majority of misbehavior—it makes them hide their intent.
OpenAI, Oracle, and SoftBank announce five new Stargate AI datacenter sites, accelerating a $500B, 10-gigawatt U.S. infrastructure buildout to power next-generation AI and create tens of thousands of jobs.