Machine Intelligence Research Institute

web

Credibility Rating

3/5

Good(3)

Good quality. Reputable source with community review or editorial standards, but less rigorous than peer-reviewed venues.

Rating inherited from publication venue: MIRI

MIRI is one of the pioneering AI safety research organizations, founded in 2000, and has significantly shaped the field's early research agenda around alignment and existential risk from advanced AI.

Metadata

Importance: 55/100homepage

Summary

The about page for the Machine Intelligence Research Institute (MIRI), a nonprofit research organization focused on ensuring that the development of smarter-than-human artificial intelligence is beneficial to humanity. MIRI conducts technical AI safety research aimed at making advanced AI systems more aligned with human values and intentions.

Key Points

•MIRI is a nonprofit dedicated to ensuring advanced AI development goes well for humanity
•The organization focuses on foundational technical research for AI alignment and safety
•MIRI operates under the premise that smarter-than-human AI poses significant existential risks if not carefully developed
•The institute is one of the earliest and most influential organizations in the AI safety research space
•MIRI's work includes both technical research and public outreach on AI risk

Cited by 1 page

Page	Type	Quality
Machine Intelligence Research Institute (MIRI)	Organization	50.0

4 FactBase facts citing this source

Entity	Property	Value	As Of
Machine Intelligence Research Institute (MIRI)	Founded Date	Jan 2000	—
Machine Intelligence Research Institute (MIRI)	Headquarters	Berkeley, CA	—
Machine Intelligence Research Institute (MIRI)	Founded By	sid_fS1tEGKuNq	—
Machine Intelligence Research Institute (MIRI)	Legal Structure	501(c)(3) nonprofit	—

Cached Content Preview

HTTP 200Fetched Apr 7, 20265 KB

About the Machine Intelligence Research Institute 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

 

 
 
 
 
 
 

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

 
 

 
 

 
 
 
 
 
 
 
 
 

 
 
 
 
 Skip to content 

 
 
 

 
 
 
 
 
 
 
 
 
 
 
 
 
 About MIRI

 
 
 
 
 The Machine Intelligence Research Institute (MIRI) is a 501(c)(3) nonprofit based in Berkeley, California. We do research and public outreach intended to help prevent human extinction from the development of artificial superintelligence (ASI).

 
 
 
 
 
 
 
 
 
 Learn more about the risks from advanced AI 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 What we do

 
 
 
 
 Founded more than 20 years ago, MIRI was among the first to recognize the future invention of artificial superintelligence as the most important—and potentially catastrophic—event in the twenty-first century. MIRI was the first organization to advocate for and work on ASI alignment as a technical problem, and has played a central role in building the field over the years.

 Unfortunately, our efforts failed to prevent the current emergency. The alignment problem is not on track to be solved before the leading companies succeed in building smarter-than-human AI, and the default outcome is human extinction. 

 Our priority now is to use the lessons we’ve learned so far to inform the world about the situation and what needs to be done. 

 Extinction from AI is a live possibility, and the only reasonable response is to stop AI development altogether, until such a time as the alignment problem has been solved.

   
 
 
 
 
 
 
 
 
 Learn more about MIRI’s research 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 History

 
 
 
 
 
 
 
 
 2000

 
 
 
 
 
 
 
 
 Eliezer Yudkowsky, along with Brian and Sabine Atkins, founded MIRI as the Singularity Institute for Artificial Intelligence with the goal of accelerating progress towards smarter-than-human AI.

 
 
 
 
 
 
 
 
 
 
 
 
 2000-2003

 
 
 
 
 
 
 
 
 Yudkowsky  realized that there would in fact be a problem of aligning smarter-than-human AI with human values. 

 MIRI pivoted to focus most research efforts on ASI alignment  (though the term “alignment” would only be coined over a decade later).

 
 
 
 
 
 
 
 
 
 
 
 
 2006-2012

 
 
 
 
 
 
 
 
 As part of his field-building efforts, Yudkowsky wrote a series of blog posts on topics including human reasoning, decision theory, morality, and AI. These writings led to the creation of the popular community blog  LessWrong , and were later  published as a book .

  

  

 MIRI co-founded and organized the  Singularity Summit , an annual conference that covered topics such as AI, brain-computer interfaces, robotics, and regenerative medicine.

 
 
 
 
 
 
 
 
 
 
 
 
 2013

 
 
 
 
 
 
 
 
 The organization changed its name from the Singularity Institute to the Machine Intelligence Research Institute.

 
 
 
 
 
 
 
 
 
 
 
 
 2013-2018

 
 
 
 
 
 
 
 
 Research focused on  foundational mathematical problems relevant to 

... (truncated, 5 KB total)

Resource ID: kb-2c16d126b367df5d | Stable ID: sid_53egE3kVax