Deep and foundational research needs to be conducted to guarantee the safety of advanced AI systems.

This work must begin swiftly to ensure they are developed and validated prior to the advent of advanced AIs.

The international community should consider setting up three clear processes to prepare for a world where advanced AI systems pose catastrophic risks:

States should agree on technical and institutional measures required to prepare for advanced AI systems, regardless of their development timescale.

In the long run, however, states will need to go further to ensure truly global governance of risks from advanced AI.

Models whose capabilities fall below early warning thresholds require only limited testing and evaluation, while more rigorous assurance mechanisms are needed for advanced AI systems exceeding these early warning thresholds.

This is insufficient to provide safety guarantees for advanced AI systems.

advanced AI systems may increasingly engage in complex multi agent interactions with other AI systems and users.

Independent research into AI safety and verification is critical to develop techniques to ensure the safety of advanced AI systems.