The AI Alignment Problem: Why It’s Hard, and Where to Start Eliezer Yudkowsky Machine Intelligence Research Institute May 5, 2016

First Page		Document Content
Date: 2017-01-30 22:06:06 Artificial intelligence Technology Motivation Metaphysics Game theory Futurology Philosophy of artificial intelligence Choice modelling Utility Expected utility hypothesis Intelligent agent Friendly artificial intelligence		The AI Alignment Problem: Why It’s Hard, and Where to Start Eliezer Yudkowsky Machine Intelligence Research Institute May 5, 2016 Add to Reading List Source URL: intelligence.org Download Document from Source Website File Size: 278,17 KB Share Document on Facebook

	Web Appendix for “Reference-Dependent Consumption Plans” by Botond K˝oszegi and Matthew Rabin Appendix A: Modeling Rational Reference-Dependent Behavior Throughout the paper, we have used the PPE solution concept to DocID: 1rosK - View Document
	Ego Utility and Information Acquisition1 Botond K} oszegi, UC Berkeley Abstract Based on extensive psychological evidence and the experience of most of us, it seems DocID: 1rbuU - View Document
	Behavioral Economics: Past, Present, Future Colin F. Camerer Division of Humanities and Social SciencesCaltech Pasadena, CA 91125 DocID: 1r5yC - View Document
	A Nonpragmatic Vindication of Probabilism Author(s): James M. Joyce Source: Philosophy of Science, Vol. 65, No. 4, (Dec., 1998), ppPublished by: The University of Chicago Press on behalf of the Philosophy of Sc DocID: 1r1GD - View Document
	Representation Theorems and Realism About Degrees of Belief" Lyle ZyndaTT Indiana University South Bend DocID: 1r0gI - View Document