AbstractMilitary and economic pressures are driving the rapid development of autonomous systems. We show that these systems are likely to behave in anti-social and harmful ways unless they are very carefully designed. Designers will be motivated to create systems that act approximately rationally and rational systems exhibit universal drives towards self-protection, resource acquisition, replication and efficiency. The current computing infrastructure would be vulnerable to unconstrained systems with these drives. We describe the use of formal methods to create provably safe but limited autonomous systems. We then discuss harmful systems and how to stop them. We conclude with a description of the 'Safe-AI Scaffolding Strategy' for creating powerful safe systems with a high confidence of safety at each stage of development.Keywords:: autonomous systemsAI safetyrationalityutility functionsrational drivesformal methods AcknowledgementsThanks to Nick Bostrom, Brad Cottel, Yoni Donner,Will Eden, Adam Ford, Ben Goertzel, Anders Sandberg, Carl Shulman, Jaan Tallinn, Michael Vassar and Rod Wallace for discussions of these issues.
Steve Omohundro (2014) studied this question.