Nate Soares heads MIRI’s research program. He first joined MIRI in 2014 as a research fellow, quickly earning a strong reputation for his strategic insight and high productivity. Nate is the primary author of most of MIRI’s agent foundations technical agenda, including the overview document “Agent Foundations for Aligning Superintelligence with Human Interests” (2014) and the AAAI paper “Corrigibility” (2015). Prior to MIRI, Nate worked as a software engineer at Google.
Senior Research Fellow
Eliezer Yudkowsky (email) is a decision theorist who is widely cited for his writings on the long-term future of artificial intelligence. His views on the social and philosophical implications of AI have had a major impact on ongoing debates in the field, and his work in mathematical logic has heavily shaped MIRI’s research agenda. He is the author of the Cambridge Handbook of Artificial Intelligence chapter “The Ethics of Artificial Intelligence” with Nick Bostrom (2014), and has written a number of popular introductions to the science of human rationality.
Benya Fallenstein (email) works on basic theoretical questions raised by the challenge of aligning advanced AI systems with human goals. These include decision- and game-theoretic problems that arise when artificial agents reason about future versions of themselves or about other, similarly powerful agents in their environment. Since joining the research team in 2014, Benya has spent time developing models of logical uncertainty (uncertainty about which mathematical statements are true), self-reference in higher-order theorem-proving systems, and the specification of safe AI goals. Benya holds a Bachelors in Mathematics from the University of Vienna.
Patrick LaVictoire (email) has a background in pure mathematics (BA from the University of Chicago, PhD from UC Berkeley, postdoc at the University of Wisconsin) and applied machine learning / data science (working for the app search startup Quixey). Patrick joined MIRI in March 2015. His research interests include the mathematics of idealized decision theory, logical counterfactuals, principled self-modification, goal stability, and corrigibility.
Jessica Taylor (email) is the lead researcher on the “Alignment for Advanced Machine Learning Systems” agenda (2016). Her research interests include problems in this agenda, logical uncertainty, and corrigibility. She has an MSc in computer science from Stanford, where she studied machine learning and probabilistic programming. Jessica joined MIRI’s team in August 2015.
Scott Garrabrant (email) earned his PhD in mathematics from UCLA studying applications of theoretical computer science to enumerative combinatorics. His main research area is in logical uncertainty, and he is the primary author of “Logical Induction” (2016), a highly general method for assigning probabilities to logical sentences. He is also interested in other aspects of logical uncertainty and counterfactuals. Scott joined MIRI’s team in December 2015.
Marcello Herreshoff (email) studied at Stanford, gaining a B.S. in Mathematics with Honors and two honorable mentions in the Putnam Mathematical Competition. He then spent five years as a software engineer at Google, where he gained a background in machine learning, before joining MIRI’s team in April 2017. His research interests include logical uncertainty and the design of reflective agents. Marcello has also volunteered with MIRI in the past to help produce results such as “Robust Cooperation in the Prisoner’s Dilemma: Program Equilibrium via Provability Logic” and “Program Equilibrium in the Prisoner’s Dilemma via Löb’s Theorem” (both 2014).
Sam Eisenstat (email) works on questions relating to the foundations of reasoning and agency. He studied pure mathematics at the University of Waterloo, where he carried out research in mathematical logic. Before joining MIRI in April 2017, he worked on automatic construction of deep learning models at Google. He currently works on logical uncertainty, and in particular is exploring analogies between current theories of logical uncertainty and Bayesian reasoning. He has also done work on decision theory and counterfactuals.
Assistant Research Fellow
Ryan Carey (email) works on designing machine learning agents that operate safely even when their value function differs from their developers’ intentions. This involves improving the robustness, transparency and corrigibility of machine learning agents. Before joining MIRI in September 2016, he studied a MSc in bioinformatics at Imperial College, where he worked on machine learning and medical image analysis. He also volunteered for the Centre for the Study of Existential Risk.
Researcher, AI Impacts
Katja Grace (email) contributes to AI Impacts, an independent research project focused on social and historical questions related to artificial intelligence outcomes. Her analyses include “Algorithmic Progress in Six Domains” (2013). She writes the blog Meteuphoric, and is sometimes a PhD student in Logic, Computation, and Methodology at Carnegie Mellon University. Katja joined MIRI in February 2014.
Research Fellow — On Leave
Andrew Critch (email) joined MIRI as a research fellow in 2015. He is currently on a two-year leave of absence to work with UC Berkeley’s Center for Human-Compatible AI. He earned his PhD in mathematics at UC Berkeley studying applications of algebraic geometry to machine learning models. During that time, he cofounded the Center for Applied Rationality and SPARC. Andrew has been offered university faculty positions in mathematics, mathematical biosciences, and philosophy, and worked as an algorithmic stock trader at Jane Street Capital. His current research interests include logical uncertainty, open source game theory, and avoiding race dynamics between nations and companies in AI development.
Chief Operating Officer
Malo Bourgon (email) oversees MIRI’s day-to-day operations and program activities. Before becoming COO, Malo worked for MIRI as a program management analyst, helping implement many of MIRI’s current systems, processes, and program activities. He also co-chairs the committee on the Safety and Beneficence of Artificial General Intelligence and Artificial Superintelligence of the IEEE Global Initiative for Ethical Considerations in Artificial Intelligence and Autonomous Systems. Malo joined MIRI in 2012 shortly after completing a master’s degree in engineering at the University of Guelph.
Program Management Analyst
Alex Vermeer (email) improves the processes and systems within and surrounding MIRI’s research team and research programs. This includes increasing the quality and quantity of workshops and similar programs, implementing best practices within the research team, coordinating the technical publication and researcher recruiting pipelines, and other research support projects. Alex holds an Engineering degree from the University of Guelph, and joined MIRI in 2012.
Research Communications Manager
Rob Bensinger (email) writes and distributes material on MIRI’s research activities. His background is in the study of scientific and religious communities, and his research interests include value theory and the relationship between philosophy and psychology. Rob joined MIRI in November 2013.
Aaron Silverbook (email) manages MIRI’s work environment. He focuses on developing, maintaining, and improving the “behind-the-scenes” systems that make the organization run like a well-oiled machine. Aaron joined MIRI in July 2016.
Colm Ó Riain
Communications and Development Strategist
Colm Ó Riain (email) coordinates our philanthropic strategy to support MIRI’s growth plans. After 15 years working in the video game industry at companies including Electronic Arts and Activision, he moved into philanthropy work at Zynga.org and Music Team before joining MIRI in July 2016. He has a master’s degree in AI from the University of Rochester and a joint honours bachelor’s in Mathematics and Computer Science. Colm is also a professional violinist and composer.
Matthew Graves (email) writes technical material to support MIRI’s research activities. His research interests are in system design, decision-making, and machine learning. He has a master’s degree in Operations Research and worked as a data scientist at Indeed before joining MIRI in October 2016.
MIRI’s 2017 research advisors are non-staff researchers who
review and contribute to our work.
Nick BostromProfessor, University of Oxford
Director, Future of Humanity Institute
Jan LeikeResearch Scientist, Google DeepMind
Steve OmohundroPhD, UC Berkeley
President, Self-Aware Systems
Stuart RussellProfessor, UC Berkeley
Director, Center for Human-Compatible AI
Author, Artificial Intelligence: A Modern Approach
Bart SelmanProfessor, Cornell University
MIRI’s 2017 general advisors correspond with us about our
organizational strategy and operations.
Gary DrescherPhD, MIT | Author, Made-Up Minds
Robin HansonProfessor, George Mason University
Jed McCalebCofounder, Stellar Development Foundation
Luke MuehlhauserResearch Analyst, Open Philanthropy Project
Christine PetersonCofounder, Foresight Institute
Jaan TallinnCofounder, Centre for the Study of Existential Risk
MIRI research associates, while primarily supported by other institutions, are active, paid,
non-staff researchers that work on projects related to MIRI’s technical agenda.
Edwin Evans CHAIRCofounder, Linc Global
Matthew Fallshaw DIRECTORFounder, TrikeApps
Anna Salamon DIRECTORPresident, Center for Applied Rationality
Nate Soares DIRECTORExecutive Director, Machine Intelligence Research Institute
Eliezer Yudkowsky DIRECTORSenior Research Fellow, Machine Intelligence Research Institute