Machine Intelligence Research Institute

The Machine Intelligence Research Institute (MIRI) is a non-profit research institute. Its mission is "to develop formal tools for the clean design and analysis of general-purpose AI systems, with the intent of making such systems safer and more reliable when they are developed."[1] It was founded in 2000 as the Singularity Institute for Artificial Intelligence by Brian Atkins, Sabine Atkins and Eliezer Yudkowsky.[2] MIRI adopted its current name in 2013.[3]

Further reading

Karnofsky, Holden (2012) Thoughts on the Singularity Institute (SI), LessWrong, May 11.

LessWrong (2020) Machine Intelligence Research Institute (MIRI), LessWrong Wiki, July 9.

Luke Muehlhauser (2015) 'Machine Intelligence Research Institute', in Ryan Carey (ed.), The Effective Altruism Handbook, 1st ed., Oxford: The Centre for Effective Altruism, pp. 127-129

Rice, Issa (2017) Timeline of Machine Intelligence Research Institute Full timeline, Timelines Wiki, June 30.

Machine Intelligence Research Institute. Official website.

Donate to MIRI.

AI alignment | Center for Applied Rationality | Eliezer Yudkowsky |  rationality community

  1. ^

    Machine Intelligence Research Institute (2021) About MIRI, Machine Intelligence Research Institute.

  2. ^

    Singularity Institute for Artificial Intelligence (2000) About SIAI, Singularity Institute for Artificial Intelligence.

  3. ^

    Muehlhauser, Luke (2013) We are now the “Machine Intelligence Research Institute” (MIRI), Machine Intelligence Research Institute, January 30.