On Controllability of AI

TL;DR

This paper argues that controlling advanced artificial general intelligence and superintelligence is fundamentally unfeasible, raising significant concerns for humanity's future and AI safety.

Contribution

It provides a multidisciplinary analysis and evidence suggesting that full control over superintelligent AI is impossible, highlighting critical implications for AI development and safety.

Findings

Advanced AI cannot be fully controlled according to multiple domain evidence.

Uncontrollability poses risks to humanity and AI safety.

Discussion of future implications of AI uncontrollability.

Abstract

Invention of artificial general intelligence is predicted to cause a shift in the trajectory of human civilization. In order to reap the benefits and avoid pitfalls of such powerful technology it is important to be able to control it. However, possibility of controlling artificial general intelligence and its more advanced version, superintelligence, has not been formally established. In this paper, we present arguments as well as supporting evidence from multiple domains indicating that advanced AI can't be fully controlled. Consequences of uncontrollability of AI are discussed with respect to future of humanity and research on AI, and AI safety and security.