Documenting the Coming Singularity

Sunday, April 26, 2009

Even AI with harmless goals will be dangerous - The Basic AI Drives

At the AGI-08 post-conference workshop, Steve Omohundro of Self-Aware Systems ( presents on his paper "The Basic AI Drives." One might imagine that AI systems with harmless goals will be harmless. The paper instead shows that intelligent systems will need to be carefully designed to prevent them from behaving in harmful ways. We identify a number of ?drives? that will appear in sufficiently advanced AI systems of any design. We call them drives because they are tendencies which will be present unless explicitly counteracted. We start by showing that goal-seeking systems will have drives to model their own operation and to improve themselves. Self-improving systems will be driven to clarify their goals and represent them as economic utility functions. They will also strive for their actions to approximate rational economic behavior. This will lead almost all systems to protect their utility functions from modification and their utility measurement systems from corruption. The paper discusses some exceptional systems which will want to modify their utility functions. We next discuss the drive toward self-protection which causes systems try to prevent themselves from being harmed. Finally we examine drives toward the acquisition of resources and toward their efficient utilization. We end with a discussion of how to incorporate these insights in designing intelligent technology which will lead to a positive future for humanity.

The Basic AI Drives from Jeriaska on Vimeo.

Read more about this on Future Current>>

Follow me on Twitter. Technological Singularity and Futurism is updated often; the easiest way to get your regular dose is by subscribing to our news feed. Stay on top of all our updates by subscribing now via RSS or Email.