Machine Intelligence Research Institute

E436709

The Machine Intelligence Research Institute is a nonprofit organization focused on developing theoretical foundations to ensure that advanced artificial intelligence systems are safe and aligned with human values.

All labels observed (5)

How this entity was disambiguated

Statements (48)

Predicate Object
instanceOf artificial intelligence research organization ⓘ
nonprofit organization ⓘ
think tank ⓘ
abbreviation MIRI ⓘ
aimsTo reduce existential risk from advanced artificial intelligence ⓘ
associatedWith LessWrong community ⓘ
linked to: LessWrong

effective altruism movement ⓘ
basedIn San Francisco Bay Area ⓘ
country United States of America ⓘ
executiveDirector Nate Soares ⓘ
focusesOn AI alignment ⓘ
artificial intelligence safety ⓘ
long-term impacts of advanced AI ⓘ
theoretical foundations of AI safety ⓘ
formerName Singularity Institute for Artificial Intelligence ⓘ
foundedBy Brian Atkins ⓘ
Eliezer Yudkowsky ⓘ
Sabrina Ford ⓘ
fundedBy individual donors ⓘ
philanthropic foundations ⓘ
hasGoal to formalize concepts such as intelligence, agency, and alignment ⓘ
hasProgram AI alignment research program ⓘ
research fellowships ⓘ
headquartersLocation Berkeley, California ⓘ
linked to: Berkeley
inception 2000 ⓘ
influencedBy existential risk research ⓘ
rationality and decision theory ⓘ
languageOfWorkOrName English ⓘ
legalForm 501(c)(3) nonprofit organization ⓘ
mission to develop formal tools for understanding and aligning advanced AI systems ⓘ
to ensure that the creation of smarter-than-human intelligence has a positive impact ⓘ
notableResearcher Benya Fallenstein ⓘ
Eliezer Yudkowsky ⓘ
Nate Soares ⓘ
Patrick LaVictoire ⓘ
Scott Garrabrant ⓘ
publishes research agendas on agent foundations ⓘ
technical research papers on AI alignment ⓘ
researchArea agent foundations ⓘ
decision theory ⓘ
embedded agency ⓘ
formal verification for AI systems ⓘ
logical uncertainty ⓘ
value alignment ⓘ
topicOf discussions in AI safety community ⓘ
website https://intelligence.org ⓘ
worksOn mathematical models of rational agency ⓘ
safety challenges of superintelligent AI systems ⓘ

How these facts were elicited

Referenced by (9)

Full triples — surface form annotated when it differs from this entity's canonical label.

Cari Tuna → hasGivenFundingTo → Machine Intelligence Research Institute ⓘ
Marcus Hutter → memberOf → Machine Intelligence Research Institute advisory board ⓘ
linked to: Machine Intelligence Research Institute
Machine Intelligence Research Institute → formerName → Singularity Institute for Artificial Intelligence ⓘ
linked to: Machine Intelligence Research Institute
Eliezer Yudkowsky → employer → Machine Intelligence Research Institute ⓘ
Eliezer Yudkowsky → workInstitution → Machine Intelligence Research Institute ⓘ
Eliezer Yudkowsky → founded → Machine Intelligence Research Institute ⓘ
LessWrong → associatedWith → Machine Intelligence Research Institute ⓘ
Carl Shulman → associatedWith → AI safety community ⓘ
linked to: Machine Intelligence Research Institute
Evan Hubinger → associatedWithOrganization → Machine Intelligence Research Institute (MIRI) ⓘ
linked to: Machine Intelligence Research Institute