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).
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.
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 humane 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 AI alignment.
MIRI ran a series of workshops which brought together researchers from a variety of backgrounds to work on problems related to AI alignment.
The MIRIx program provided funding and support for groups of researchers around the world to run their own workshops.
2017
Observing trends in the funding and progress of AI projects, MIRI leadership became more concerned that smarter-than-human AI might arrive in the relatively near future.
MIRI tried exploring a new set of engineering-heavy alignment research directions, in addition to its existing research program.
2020
Progress on the AI alignment problem continued to move slowly both at MIRI and in the field as a whole. MIRI leadership became pessimistic that the field or the organization’s existing research directions would bear fruit in time, and began a major pivot to chasing what scraps of hope remained.
2021-2022
MIRI published several write-ups about the strategic landscape of AI risks, as well as a series of dialogues with other AI alignment researchers.
2023
The success of ChatGPT sparked a much wider discussion about extinction risk from AI than had existed before.
MIRI shifted much of its focus to communicating about the topic to a broad audience, including appearing at major political forums.
2024
MIRI began expanding its communications team in order to carry out projects intended to communicate to policymakers and the general public about the developing catastrophe of smarter-than-human AI systems and launched a program to work on technical AI governance.
