Ma­chine In­tel­li­gence Re­search Institute

TagLast edit: 5 May 2021 12:51 UTC by Pablo

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.” (Machine Intelligence Research Institute 2021) It was founded in 2000 as the Singularity Institute for Artificial Intelligence by Brian Atkins, Sabine Atkins and Eliezer Yudkowsky (Singularity Institute for Artificial Intelligence 2006). MIRI adopted its current name in 2013 (Muehlhauser 2013).


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

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

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

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

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.

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

External links

Machine Intelligence Research Institute. Official website.

Related entries

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

2020 AI Align­ment Liter­a­ture Re­view and Char­ity Comparison

Larks21 Dec 2020 15:25 UTC
134 points
14 comments68 min readEA link

MIRI’s 2018 Fundraiser

malo27 Nov 2018 6:22 UTC
20 points
1 comment7 min readEA link

MIRI’s 2019 Fundraiser

malo7 Dec 2019 0:30 UTC
19 points
2 comments9 min readEA link

MIRI Up­date and Fundrais­ing Case

So8res9 Oct 2016 22:05 UTC
18 points
17 comments10 min readEA link

MIRI Sum­mer Fel­lows Pro­gram: Ap­pli­ca­tions open

colm23 Feb 2019 4:49 UTC
13 points
1 comment2 min readEA link

MIRI is seek­ing an Office Man­ager /​ Force Multiplier

RobBensinger5 Jul 2015 19:02 UTC
8 points
1 commentEA link

MIRI 2017 Fundraiser and Strat­egy Update

malo1 Dec 2017 20:06 UTC
6 points
4 commentsEA link

MIRI posts its tech­ni­cal re­search agenda [link]

RyanCarey24 Dec 2014 0:27 UTC
4 points
1 commentEA link

Ask MIRI Any­thing (AMA)

RobBensinger11 Oct 2016 19:54 UTC
18 points
80 commentsEA link

CHCAI/​MIRI re­search in­tern­ship in AI safety

Beth_Barnes17 Feb 2017 11:26 UTC
14 points
3 commentsEA link

My cur­rent thoughts on MIRI’s “highly re­li­able agent de­sign” work

Daniel_Dewey7 Jul 2017 1:17 UTC
50 points
64 commentsEA link

Why I’m donat­ing to MIRI this year

Owen_Cotton-Barratt30 Nov 2016 22:21 UTC
34 points
32 commentsEA link

I’m Buck Sh­legeris, I do re­search and out­reach at MIRI, AMA

Buck15 Nov 2019 22:44 UTC
122 points
231 comments2 min readEA link

In­tro to car­ing about AI al­ign­ment as an EA cause

So8res14 Apr 2017 0:42 UTC
24 points
12 commentsEA link
No comments.