To minimize these risks as AI models continue to improve, we're building a new team called Readiness. Led by Aleksander Madry, the readiness team will closely link capability assessment, evaluations and internal red teaming for frontier models, from the models we are developing in the near future to those with AGI-level capabilities. The team will help monitor, assess, predict and protect against catastrophic risks spanning multiple categories including:

• Individualized persuasion
• Cyber ​​security
• Chemical, biological, radiological and nuclear (CBRN) threats
• Autonomous replication and adaptation (ARA)

The Preparedness Team's mission also includes developing and maintaining a risk-informed development policy (RDP). Our RDP will detail our approach to developing rigorous boundary model capability assessments and monitoring, creating a spectrum of protective actions, and establishing a governance structure for accountability and oversight of this development process. The RDP is intended to complement and extend our existing risk mitigation work, contributing to the security and alignment of new, highly capable systems, both pre- and post-deployment.