Machine Intelligence Research Institute - Wikipedia

[Jump to content](https://en.wikipedia.org/wiki/Machine_Intelligence_Research_Institute#bodyContent)

From Wikipedia, the free encyclopedia

Nonprofit AI safety organization

"Singularity Institute" redirects here; not to be confused with [Singularity University](https://en.wikipedia.org/wiki/Singularity_University "Singularity University").

| [![](https://upload.wikimedia.org/wikipedia/en/thumb/0/04/MIRI_logo.svg/250px-MIRI_logo.svg.png)](https://en.wikipedia.org/wiki/File:MIRI_logo.svg) |
| Formation | 2000; 26 years ago (2000) |
| Type | [Nonprofit](https://en.wikipedia.org/wiki/Nonprofit "Nonprofit") [research institute](https://en.wikipedia.org/wiki/Research_institute "Research institute") |
| [Tax ID no.](https://en.wikipedia.org/wiki/Taxpayer_Identification_Number "Taxpayer Identification Number") | 58-2565917 |
| Purpose | Research into [friendly artificial intelligence](https://en.wikipedia.org/wiki/Friendly_artificial_intelligence "Friendly artificial intelligence") and the [AI control problem](https://en.wikipedia.org/wiki/AI_control_problem "AI control problem") |
| Location | - [Berkeley, California](https://en.wikipedia.org/wiki/Berkeley,_California "Berkeley, California"), [U.S.](https://en.wikipedia.org/wiki/U.S. "U.S.") |
| Key people | [Eliezer Yudkowsky](https://en.wikipedia.org/wiki/Eliezer_Yudkowsky "Eliezer Yudkowsky") |
| Website | [intelligence.org](http://intelligence.org/)[![Edit this at Wikidata](https://upload.wikimedia.org/wikipedia/en/thumb/8/8a/OOjs_UI_icon_edit-ltr-progressive.svg/20px-OOjs_UI_icon_edit-ltr-progressive.svg.png)](https://www.wikidata.org/wiki/Q2040269#P856 "Edit this at Wikidata") |

Machine Intelligence Research Institute

The **Machine Intelligence Research Institute** ( **MIRI**), formerly the **Singularity Institute for Artificial Intelligence** ( **SIAI**), is a [non-profit](https://en.wikipedia.org/wiki/Non-profit_organization "Non-profit organization") [research institute](https://en.wikipedia.org/wiki/Research_institute "Research institute") focused since 2005 on identifying and managing potential [existential risks from artificial intelligence](https://en.wikipedia.org/wiki/Existential_risk_from_artificial_intelligence "Existential risk from artificial intelligence"). MIRI's work has focused on a [friendly AI](https://en.wikipedia.org/wiki/Friendly_artificial_intelligence "Friendly artificial intelligence") approach to system design and on predicting the rate of technology development.

## History

\[ [edit](https://en.wikipedia.org/w/index.php?title=Machine_Intelligence_Research_Institute&action=edit&section=1 "Edit section: History")\]

[![](https://upload.wikimedia.org/wikipedia/commons/thumb/3/35/Eliezer_Yudkowsky%2C_Stanford_2006_%28square_crop%29.jpg/250px-Eliezer_Yudkowsky%2C_Stanford_2006_%28square_crop%29.jpg)](https://en.wikipedia.org/wiki/File:Eliezer_Yudkowsky,_Stanford_2006_(square_crop).jpg) [Yudkowsky](https://en.wikipedia.org/wiki/Eliezer_Yudkowsky "Eliezer Yudkowsky") at [

... (truncated, 48 KB total)