Eliezer Yudkowsky
Founder and research fellow at the Machine Intelligence Research Institute
A researcher and writer who helped popularize the idea of friendly AI and founded the Machine Intelligence Research Institute.
Biography
Eliezer Yudkowsky is an American artificial intelligence researcher and writer on decision theory and ethics, known for popularizing ideas related to friendly artificial intelligence. He is the founder of and a research fellow at the Machine Intelligence Research Institute (MIRI), a nonprofit in Berkeley, California.
His work on the prospect of a runaway intelligence explosion influenced Nick Bostrom's 2014 book Superintelligence. In 2004 he proposed coherent extrapolated volition, a theoretical AI alignment framework in which systems pursue what people would desire under ideal epistemic and moral conditions. His views on friendly AI are cited in Stuart Russell and Peter Norvig's textbook Artificial Intelligence: A Modern Approach. He co-authored the New York Times bestseller If Anyone Builds It, Everyone Dies with Nate Soares.
Notable contributions
Founded the Machine Intelligence Research Institute
Founded MIRI, a private research nonprofit in Berkeley, California, focused on AI alignment and safety research.
Proposed coherent extrapolated volition
Proposed in 2004 a theoretical AI alignment framework in which AI is designed to pursue what people would desire under ideal epistemic and moral conditions.
Co-authored If Anyone Builds It, Everyone Dies
With Nate Soares, wrote a New York Times bestseller arguing that superhuman AI built with current methods would be catastrophically dangerous.