On Controllability of AI
This addresses a foundational problem for AI safety and security, with potential broad implications for the future of humanity, but it is incremental as it builds on existing concerns without new empirical results.
The paper tackles the problem of controlling artificial general intelligence and superintelligence, arguing with evidence that advanced AI cannot be fully controlled, and discusses the consequences for humanity and AI safety.
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.