A Safe Ethical System for Intelligent Machines

Presentation Powerpoint * Proceedings PDF presented Nov. 6, 2009 at the AAAI 2009 Fall Symposium on Biologically Inspired Cognitive Architectures (Washington, DC)

As machines become more intelligent and take on more responsibilities, their decision-making capabilities must be informed and constrained by a coherent, integrated moral/ethical structure with no internal inconsistencies for everyone’s safety and well-being. Unfortunately, no such structure is currently agreed upon to exist. We propose to solve this problem by a) drawing upon experimental evidence and lessons learned from evolution and economics to show that morality is actually objective and derivable from first principles; b) presenting a coherent, integrated, platonic ethical system with no internal inconsistencies that flows naturally from a single high-level logically-derived Kantian imperative to low-level reflexive “rules of thumb” that match current human sensibilities; and c) suggesting a biologically-inspired architecture which supports and enforces this system which can be relatively easily implemented.

What Is Artificial General Intelligence? Clarifying The Goal For Engineering And Evaluation

Video * Proceedings PDF presented March 7, 2009 at The Second Conference on Artificial General Intelligence (Arlington, VA)

Artificial general intelligence (AGI) has no consensus definition but everyone believes that they will recognize it when it appears. Unfortunately, in reality, there is great debate over specific examples that range the gamut from exact human brain simulations to infinitely capable systems.

Indeed, it has even been argued whether specific instances of humanity are truly generally intelligent. Lack of a consensus definition seriously hampers effective discussion, design, development, and evaluation of generally intelligent systems. We will address this by proposing a goal for AGI, rigorously defining one specific class of general intelligence architecture that fulfills this goal that a number of the currently active AGI projects appear to be converging towards, and presenting a simplified view intended to promote new research in order to facilitate the creation of a safe artificial general intelligence.