Katana VentraIP

Machine Intelligence Research Institute

The Machine Intelligence Research Institute (MIRI), formerly the Singularity Institute for Artificial Intelligence (SIAI), is a non-profit research institute focused since 2005 on identifying and managing potential existential risks from artificial general intelligence. MIRI's work has focused on a friendly AI approach to system design and on predicting the rate of technology development.

"Singularity Institute" redirects here. Not to be confused with Singularity University.

Formation

2000 (2000)

Nonprofit research institute

Research into friendly artificial intelligence and the AI control problem

Eliezer Yudkowsky

intelligence.org

Graves, Matthew (8 November 2017). . Skeptic. The Skeptics Society. Retrieved 28 July 2018.

"Why We Should Be Concerned About Artificial Superintelligence"

LaVictoire, Patrick; Fallenstein, Benja; ; Bárász, Mihály; Christiano, Paul; Herreshoff, Marcello (2014). "Program Equilibrium in the Prisoner's Dilemma via Löb's Theorem". Multiagent Interaction without Prior Coordination: Papers from the AAAI-14 Workshop. AAAI Publications.

Yudkowsky, Eliezer

Soares, Nate; Levinstein, Benjamin A. (2017). (PDF). Formal Epistemology Workshop (FEW). Retrieved 28 July 2018.

"Cheating Death in Damascus"

Soares, Nate; Fallenstein, Benja; ; Armstrong, Stuart (2015). "Corrigibility". AAAI Workshops: Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, TX, January 25–26, 2015. AAAI Publications.

Yudkowsky, Eliezer

Soares, Nate; Fallenstein, Benja (2015). (PDF). In Miller, James; Yampolskiy, Roman; Armstrong, Stuart; et al. (eds.). The Technological Singularity: Managing the Journey. Springer.

"Aligning Superintelligence with Human Interests: A Technical Research Agenda"

(2008). "Artificial Intelligence as a Positive and Negative Factor in Global Risk" (PDF). In Bostrom, Nick; Ćirković, Milan (eds.). Global Catastrophic Risks. Oxford University Press. ISBN 978-0199606504.

Yudkowsky, Eliezer

Taylor, Jessica (2016). . Workshops at the Thirtieth AAAI Conference on Artificial Intelligence.

"Quantilizers: A Safer Alternative to Maximizers for Limited Optimization"

(2011). "Complex Value Systems in Friendly AI" (PDF). Artificial General Intelligence: 4th International Conference, AGI 2011, Mountain View, CA, USA, August 3–6, 2011. Berlin: Springer.

Yudkowsky, Eliezer

Allen Institute for Artificial Intelligence

Future of Humanity Institute

Institute for Ethics and Emerging Technologies

Russell, Stuart; Dewey, Daniel; Tegmark, Max (Winter 2015). "Research Priorities for Robust and Beneficial Artificial Intelligence". AI Magazine. 36 (4): 6. :1602.03506. Bibcode:2016arXiv160203506R. doi:10.1609/aimag.v36i4.2577.

arXiv

Official website