ABSTRACT
In this chapter, I review specific proposals aimed at creating restricted environments for safely interacting with artificial minds. I evaluate the feasibility of the proposals presented and suggest a protocol aimed at enhancing the safety and security of such methodologies. Although it is unlikely that long-term and secure confinement of AI is possible, I am hopeful that the proposed protocol will give researchers a little more time to find a permanent and satisfactory solution for addressing existential risks associated with the appearance of superintelligent machines.
