Machine Intelligence Research Institute

From Effective Altruism Wiki
Jump to navigation Jump to search
This page has been flagged as a stub. Please help by expanding this page.

Machine Intelligence Research Institute
Causes Existential Risk Reduction, AI Security/Risk
Type
Research, Outreach, Advocacy
Headquarters Berkeley, California, United States
Operates in United States

The Machine Intelligence Research Institute (MIRI) is a research nonprofit studying the long-term impact of advances in artificial intelligence (AI). MIRI's goal is to develop the mathematical tools needed to make smarter-than-human AI software safe and beneficial. MIRI's FAQ page breaks its research program down into three focus areas, described in more detail in the organization's technical agenda:

  • highly reliable agent design — learning how to specify highly autonomous systems that reliably pursue some fixed goal;
  • value specification — supplying autonomous systems with the intended goals; and
  • error tolerance — making such systems robust to programmer error.

MIRI was co-founded in 2000 by Eliezer Yudkowsky, Sabine Atkins, and Brian Atkins. The current executive director of MIRI is Nate Soares, who was originally hired as a research fellow in 2014. Mr. Soares took over from the former executive director, Luke Muehlhauser, in 2015. MIRI was formerly known under other names, the Singularity Institute for Artificial Intelligence (SIAI), and then just the Singularity Institute (SI). The organization rebranded as MIRI in 2013.

External links