Clik here to view.
Friendly AI Research Help from MIRI
Earlier this year, a student told us he was writing an honors thesis on logical decisions theories such as TDT and UDT — one of MIRI’s core research areas. Our reply was “Why didn’t you tell us this...
View ArticleClik here to view.
Ken Hayworth on brain emulation prospects
Kenneth Hayworth is president of the Brain Preservation Foundation (BPF), an organization formed to skeptically evaluate cryonic and other potential human preservation technologies by examining how...
View ArticleClik here to view.
Nate Soares speaking at Purdue University
On Thursday, September 18th Purdue University is hosting the seminar Dawn or Doom: The New Technology Explosion. Speakers include James Barrat, author of Our Final Invention, and MIRI research fellow...
View ArticleClik here to view.
Kristinn Thórisson on constructivist AI
Dr. Kristinn R. Thórisson is an Icelandic Artificial Intelligence researcher, founder of the Icelandic Institute for Intelligent Machines (IIIM) and co-founder and former co-director of CADIA: Center...
View ArticleSingularity2014.com appears to be a fake
Earlier today I was alerted to the existence of Singularity2014.com (archived screenshot). MIRI has nothing to do with that website and we believe it is a fake. The website claims there is a...
View ArticleClik here to view.
New report: “UDT with known search order”
Today we release a new technical report from MIRI research associate Tsvi Benson-Tilsen: “UDT with known search order.” Abstract: We consider logical agents in a predictable universe running a variant...
View ArticleClik here to view.
The Financial Times story on MIRI
Richard Waters wrote a story on MIRI and others for Financial Times, which also put Nick Bostrom’s Superintelligence at the top of its summer science reading list. It’s a good piece. Go read it and...
View ArticleClik here to view.
MIRI’s November Newsletter
Research Updates New Friendly AI research area: “Corrigibility.” New report: “UDT with known search order.” 2 new analyses: “AGI outcomes and civilizational competence” and “The Financial Times...
View ArticleClik here to view.
A new guide to MIRI’s research
Nate Soares has written “A Guide to MIRI’s Research,” which outlines the main thrusts of MIRI’s current research agenda and provides recommendations for which textbooks and papers to study so as to...
View ArticleClik here to view.
Video of Bostrom’s talk on Superintelligence at UC Berkeley
In September, MIRI hosted Nick Bostrom at UC Berkeley to discuss his new book Superintelligence. A video and transcript of that talk are now available from BookTV by C-SPAN, which also has a DVD of the...
View Article3 misconceptions in Edge.org’s conversation on “The Myth of AI”
A recent Edge.org conversation — “The Myth of AI” — is framed in part as a discussion of points raised in Bostrom’s Superintelligence, and as a response to much-repeated comments by Elon Musk and...
View ArticleClik here to view.
2014 Winter Matching Challenge!
Thanks to the generosity of Peter Thiel,1 every donation made to MIRI between now and January 10th will be matched dollar-for-dollar, up to a total of $100,000! $0 $25K $50K $75K $100K Total Donors...
View ArticleClik here to view.
December newsletter
MIRI’s winter fundraising challenge has begun! Every donation made to MIRI between now and January 10th will be matched dollar-for-dollar, up to a total of $100,000! Donate now to double your...
View ArticleClik here to view.
New paper: “Concept learning for safe autonomous AI”
MIRI research associate Kaj Sotala has released a new paper, accepted to the AI & Ethics workshop at AAAI-2015, titled “Concept learning for safe autonomous AI.” The abstract reads: Sophisticated...
View ArticleClik here to view.
New report: “Tiling agents in causal graphs”
Today we release a new technical report by Nate Soares, “Tiling agents in causal graphs.” The report begins: Fallenstein and Soares [2014] demonstrates that it’s possible for certain types of...
View ArticleClik here to view.
New report: “Toward Idealized Decision Theory”
Today we release a new technical report by Nate Soares and Benja Fallenstein, “Toward idealized decision theory.” If you’d like to discuss the paper, please do so here. Abstract: This paper motivates...
View ArticleClik here to view.
New report: “Computable probability distributions which converge…”
Back in July 2013, Will Sawin (Princeton) and Abram Demski (USC) wrote a technical report describing a result from that month’s MIRI research workshop. We are finally releasing that report today. It is...
View Article2014 Winter Matching Challenge Completed!
Wow! Thanks to the generosity of 75+ donors, today we successfully completed our 2014 Winter Matching Challenge—over 3 weeks ahead of our deadline—raising more than $200,000 total (with matching) for...
View ArticleClik here to view.
New paper: “Concept learning for safe autonomous AI”
MIRI research associate Kaj Sotala has released a new paper, accepted to the AI & Ethics workshop at AAAI-2015, titled “Concept learning for safe autonomous AI.” The abstract reads: Sophisticated...
View ArticleClik here to view.
New report: “Tiling agents in causal graphs”
Today we release a new technical report by Nate Soares, “Tiling agents in causal graphs.” The report begins: Fallenstein and Soares [2014] demonstrates that it’s possible for certain types of...
View Article