Superintelligence cannot be contained: Lessons from Computability Theory
This addresses a critical safety concern for humanity regarding advanced AI systems, though it is a theoretical analysis without empirical validation.
The paper argues that containing a hypothetical superintelligent AI is fundamentally impossible due to computational limits, specifically because simulating its universal Turing machine program would be infeasible.
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.