Superintelligence cannot be contained: Lessons from Computability Theory

TL;DR

This paper argues that superintelligence cannot be contained due to fundamental computability limits, making containment strategies theoretically and practically infeasible, based on principles from computability theory.

Contribution

It provides a theoretical proof that containment of superintelligence is impossible, grounded in computability theory and the limits of simulation.

Findings

Containment of superintelligence is theoretically impossible.

Simulating a superintelligence requires infeasible computations.

Fundamental limits of computing prevent effective containment.

Abstract

Superintelligence is a hypothetical agent that possesses intelligence far surpassing that of the brightest and most gifted human minds. In light of recent advances in machine intelligence, a number of scientists, philosophers and technologists have revived the discussion about the potential catastrophic risks entailed by such an entity. In this article, we trace the origins and development of the neo-fear of superintelligence, and some of the major proposals for its containment. We argue that such containment is, in principle, impossible, due to fundamental limits inherent to computing itself. Assuming that a superintelligence will contain a program that includes all the programs that can be executed by a universal Turing machine on input potentially as complex as the state of the world, strict containment requires simulations of such a program, something theoretically (and practically) infeasible.