All Posts
MIRI Newsletter #123 July 3, 2025
IABIED: Advertisement design competition July 1, 2025
A case for courage, when speaking of AI danger June 26, 2025
So You Want to Work at a Frontier AI Lab June 11, 2025
Thoughts on AI 2027 April 9, 2025
MIRI Communications Team 2024 Recap April 3, 2025
Takeover Not Required March 14, 2025
MIRI Newsletter #121 February 6, 2025
Communications in Hard Mode December 13, 2024
MIRI’s 2024 End-of-Year Update December 2, 2024
October 2024 Newsletter October 29, 2024
September 2024 Newsletter September 16, 2024
July 2024 Newsletter July 10, 2024
June 2024 Newsletter June 14, 2024
MIRI 2024 Communications Strategy May 29, 2024
May 2024 Newsletter May 14, 2024
April 2024 Newsletter April 12, 2024
MIRI 2024 Mission and Strategy Update January 4, 2024
Written statement of MIRI CEO Malo Bourgon to the AI Insight Forum December 6, 2023
AI as a science, and three obstacles to alignment strategies October 30, 2023
Announcing MIRI’s new CEO and leadership team October 10, 2023
The basic reasons I expect AGI ruin April 21, 2023
Misgeneralization as a misnomer April 10, 2023
Deep Deceptiveness March 21, 2023
Yudkowsky on AGI risk on the Bankless podcast March 14, 2023
July 2022 Newsletter July 30, 2022
AGI Ruin: A List of Lethalities June 10, 2022
Shah and Yudkowsky on alignment failures March 2, 2022
January 2022 Newsletter January 31, 2022
December 2021 Newsletter December 31, 2021
Ngo’s view on alignment difficulty December 14, 2021
Conversation on technology forecasting and gradualism December 9, 2021
More Christiano, Cotra, and Yudkowsky on AI progress December 6, 2021
Shulman and Yudkowsky on AI progress December 4, 2021
Biology-Inspired AGI Timelines: The Trick That Never Works December 3, 2021
Visible Thoughts Project and Bounty Announcement November 29, 2021
Christiano, Cotra, and Yudkowsky on AI progress November 25, 2021
Yudkowsky and Christiano discuss “Takeoff Speeds” November 22, 2021
Ngo and Yudkowsky on AI capability gains November 18, 2021
Ngo and Yudkowsky on alignment difficulty November 15, 2021
Discussion with Eliezer Yudkowsky on AGI interventions November 11, 2021
November 2021 Newsletter November 6, 2021
October 2021 Newsletter October 7, 2021
September 2021 Newsletter September 29, 2021
August 2021 Newsletter August 31, 2021
July 2021 Newsletter August 3, 2021
June 2021 Newsletter July 1, 2021
Finite Factored Sets May 23, 2021
May 2021 Newsletter May 18, 2021
April 2021 Newsletter May 2, 2021
March 2021 Newsletter April 1, 2021
February 2021 Newsletter March 2, 2021
January 2021 Newsletter January 27, 2021
December 2020 Newsletter December 30, 2020
2020 Updates and Strategy December 21, 2020
November 2020 Newsletter November 30, 2020
October 2020 Newsletter October 23, 2020
September 2020 Newsletter September 10, 2020
August 2020 Newsletter August 13, 2020
July 2020 Newsletter July 8, 2020
June 2020 Newsletter June 8, 2020
May 2020 Newsletter May 29, 2020
April 2020 Newsletter May 1, 2020
MIRI’s largest grant to date! April 27, 2020
March 2020 Newsletter April 1, 2020
February 2020 Newsletter February 23, 2020
Our 2019 Fundraiser Review February 13, 2020
January 2020 Newsletter January 15, 2020
December 2019 Newsletter December 5, 2019
MIRI’s 2019 Fundraiser December 2, 2019
Giving Tuesday 2019 November 28, 2019
November 2019 Newsletter November 25, 2019
October 2019 Newsletter October 25, 2019
September 2019 Newsletter September 30, 2019
August 2019 Newsletter August 6, 2019
July 2019 Newsletter July 19, 2019
New paper: “Risks from learned optimization” June 7, 2019
June 2019 Newsletter June 1, 2019
2018 in review May 31, 2019
May 2019 Newsletter May 10, 2019
New paper: “Delegative reinforcement learning” April 24, 2019
April 2019 Newsletter April 21, 2019
New grants from the Open Philanthropy Project and BERI April 1, 2019
March 2019 Newsletter March 14, 2019
Applications are open for the MIRI Summer Fellows Program! March 10, 2019
A new field guide for MIRIx March 9, 2019
February 2019 Newsletter February 25, 2019
Thoughts on Human Models February 22, 2019
Our 2018 Fundraiser Review February 11, 2019
January 2019 Newsletter January 31, 2019
December 2018 Newsletter December 16, 2018
Announcing a new edition of “Rationality: From AI to Zombies” December 15, 2018
2017 in review November 28, 2018
November 2018 Newsletter November 26, 2018
2018 Update: Our New Research Directions November 22, 2018
Embedded Curiosities November 8, 2018
Subsystem Alignment November 6, 2018
Robust Delegation November 4, 2018
Embedded World-Models November 2, 2018
Decision Theory October 31, 2018
October 2018 Newsletter October 29, 2018
The Rocket Alignment Problem October 3, 2018
September 2018 Newsletter September 30, 2018
Summer MIRI Updates September 1, 2018
August 2018 Newsletter August 27, 2018
July 2018 Newsletter July 25, 2018
New paper: “Forecasting using incomplete models” June 27, 2018
June 2018 Newsletter June 23, 2018
May 2018 Newsletter May 31, 2018
April 2018 Newsletter April 10, 2018
2018 research plans and predictions March 31, 2018
New paper: “Categorizing variants of Goodhart’s Law” March 27, 2018
March 2018 Newsletter March 25, 2018
Sam Harris and Eliezer Yudkowsky on “AI: Racing Toward the Brink” February 28, 2018
February 2018 Newsletter February 25, 2018
January 2018 Newsletter January 28, 2018
Fundraising success! January 10, 2018
End-of-the-year matching challenge! December 14, 2017
ML Living Library Opening December 12, 2017
A reply to Francois Chollet on intelligence explosion December 6, 2017
MIRI’s 2017 Fundraiser December 1, 2017
Security Mindset and the Logistic Success Curve November 26, 2017
Security Mindset and Ordinary Paranoia November 25, 2017
Announcing “Inadequate Equilibria” November 16, 2017
A major grant from the Open Philanthropy Project November 8, 2017
November 2017 Newsletter November 3, 2017
New paper: “Functional Decision Theory” October 22, 2017
AlphaGo Zero and the Foom Debate October 20, 2017
October 2017 Newsletter October 16, 2017
There’s No Fire Alarm for Artificial General Intelligence October 13, 2017
September 2017 Newsletter September 24, 2017
New paper: “Incorrigibility in the CIRL Framework” August 31, 2017
August 2017 Newsletter August 16, 2017
July 2017 Newsletter July 25, 2017
Updates to the research team, and a major donation July 4, 2017
June 2017 Newsletter June 16, 2017
May 2017 Newsletter May 10, 2017
2017 Updates and Strategy April 30, 2017
Decisions are for making bad outcomes inconsistent April 7, 2017
April 2017 Newsletter April 6, 2017
Two new researchers join MIRI March 31, 2017
2016 in review March 28, 2017
New paper: “Cheating Death in Damascus” March 18, 2017
March 2017 Newsletter March 15, 2017
Using machine learning to address AI risk February 28, 2017
February 2017 Newsletter February 16, 2017
CHCAI/MIRI research internship in AI safety February 11, 2017
New paper: “Toward negotiable reinforcement learning” January 25, 2017
Response to Cegłowski on superintelligence January 13, 2017
January 2017 Newsletter January 4, 2017
New paper: “Optimal polynomial-time estimators” December 31, 2016
AI Alignment: Why It’s Hard, and Where to Start December 28, 2016
December 2016 Newsletter December 13, 2016
November 2016 Newsletter November 20, 2016
Post-fundraiser update November 11, 2016
White House submissions and report on AI safety October 20, 2016
MIRI AMA, and a talk on logical induction October 11, 2016
October 2016 Newsletter October 9, 2016
CSRBAI talks on agent models and multi-agent dilemmas October 6, 2016
MIRI’s 2016 Fundraiser September 16, 2016
New paper: “Logical induction” September 12, 2016
Grant announcement from the Open Philanthropy Project September 6, 2016
September 2016 Newsletter September 3, 2016
CSRBAI talks on preference specification August 30, 2016
CSRBAI talks on robustness and error-tolerance August 15, 2016
MIRI strategy update: 2016 August 5, 2016
August 2016 Newsletter August 3, 2016
2016 summer program recap August 2, 2016
2015 in review July 29, 2016
Submission to the OSTP on AI outcomes July 23, 2016
July 2016 Newsletter July 5, 2016
June 2016 Newsletter June 12, 2016
New paper: “Safely interruptible agents” June 1, 2016
May 2016 Newsletter May 13, 2016
New papers dividing logical uncertainty into two subproblems April 21, 2016
April 2016 Newsletter April 11, 2016
MIRI has a new COO: Malo Bourgon March 30, 2016
Announcing a new colloquium series and fellows program March 28, 2016
March 2016 Newsletter March 5, 2016
John Horgan interviews Eliezer Yudkowsky March 2, 2016
New paper: “Defining human values for value learners” February 29, 2016
February 2016 Newsletter February 6, 2016
End-of-the-year fundraiser and grant successes January 12, 2016
January 2016 Newsletter January 3, 2016
Safety engineering, target selection, and alignment theory December 31, 2015
The need to scale MIRI’s methods December 23, 2015
Jed McCaleb on Why MIRI Matters December 15, 2015
OpenAI and other news December 11, 2015
New paper: “Proof-producing reflection for HOL” December 4, 2015
December 2015 Newsletter December 3, 2015
MIRI’s 2015 Winter Fundraiser! December 1, 2015
New paper: “Quantilizers” November 29, 2015
New paper: “Formalizing convergent instrumental goals” November 26, 2015
November 2015 Newsletter November 3, 2015
Edge.org contributors discuss the future of AI November 1, 2015
New report: “Leó Szilárd and the Danger of Nuclear Weapons” October 7, 2015
October 2015 Newsletter October 3, 2015
New paper: “Asymptotic logical uncertainty and the Benford test” September 30, 2015
September 2015 Newsletter September 14, 2015
Our summer fundraising drive is complete! September 1, 2015
Final fundraiser day: Announcing our new team August 31, 2015
AI and Effective Altruism August 28, 2015
Powerful planners, not sentient software August 18, 2015
What Sets MIRI Apart? August 14, 2015
Assessing our past and potential impact August 10, 2015
Target 3: Taking It To The Next Level August 7, 2015
When AI Accelerates AI August 3, 2015
August 2015 Newsletter August 2, 2015
A new MIRI FAQ, and other announcements July 31, 2015
MIRI’s Approach July 27, 2015
Four Background Claims July 24, 2015
Why Now Matters July 20, 2015
Targets 1 and 2: Growing MIRI July 18, 2015
MIRI’s 2015 Summer Fundraiser! July 17, 2015
An Astounding Year July 16, 2015
July 2015 Newsletter July 5, 2015
Grants and fundraisers July 1, 2015
June 2015 Newsletter June 1, 2015
Introductions May 31, 2015
Two papers accepted to AGI-15 May 29, 2015
A fond farewell and a new Executive Director May 6, 2015
May 2015 Newsletter May 1, 2015
New papers on reflective oracles and agents April 28, 2015
April 2015 newsletter April 1, 2015
Recent AI control brainstorming by Stuart Armstrong March 27, 2015
2014 in review March 22, 2015
Rationality: From AI to Zombies March 12, 2015
Bill Hibbard on Ethical Artificial Intelligence March 9, 2015
March 2015 newsletter March 1, 2015
Davis on AI capability and motivation February 6, 2015
New annotated bibliography for MIRI’s technical agenda February 5, 2015
New mailing list for MIRI math/CS papers only February 3, 2015
February 2015 Newsletter February 1, 2015
New report: “The value learning problem” January 29, 2015
New report: “Formalizing Two Problems of Realistic World Models” January 22, 2015
An improved “AI Impacts” website January 11, 2015
New report: “Questions of reasoning under logical uncertainty” January 9, 2015
Brooks and Searle on AI volition and timelines January 8, 2015
Matthias Troyer on Quantum Computers January 7, 2015
January 2015 Newsletter January 1, 2015
Our new technical research agenda overview December 23, 2014
2014 Winter Matching Challenge Completed! December 18, 2014
New report: “Computable probability distributions which converge…” December 16, 2014
New paper: “Concept learning for safe autonomous AI” December 5, 2014
December newsletter December 1, 2014
Three misconceptions in Edge.org’s conversation on “The Myth of AI” November 18, 2014
Video of Bostrom’s talk on Superintelligence at UC Berkeley November 6, 2014
MIRI’s November Newsletter November 1, 2014
The Financial Times story on MIRI October 31, 2014
New report: “UDT with known search order” October 30, 2014
Singularity2014.com appears to be a fake October 27, 2014
New paper: “Corrigibility” October 18, 2014
AGI outcomes and civilizational competence October 16, 2014
Nate Soares’ talk: “Why ain’t you rich?” October 7, 2014
MIRI’s October Newsletter October 1, 2014
Kristinn Thórisson on constructivist AI September 14, 2014
Nate Soares speaking at Purdue University September 12, 2014
Ken Hayworth on brain emulation prospects September 9, 2014
Friendly AI Research Help from MIRI September 8, 2014
John Fox on AI safety September 4, 2014
MIRI’s September Newsletter September 1, 2014
Superintelligence reading group August 31, 2014
New paper: “Exploratory engineering in artificial intelligence” August 22, 2014
2014 Summer Matching Challenge Completed! August 15, 2014
MIRI’s recent effective altruism talks August 11, 2014
Groundwork for AGI safety engineering August 4, 2014
MIRI’s August 2014 newsletter August 1, 2014
Scott Frickel on intellectual movements July 28, 2014
2014 Summer Matching Challenge! July 21, 2014
MIRI’s July 2014 newsletter July 1, 2014
Our mid-2014 strategic plan June 11, 2014
MIRI’s June 2014 Newsletter June 1, 2014
Milind Tambe on game theory in security applications May 30, 2014
Lennart Beringer on the Verified Software Toolchain May 27, 2014
Johann Schumann on high-assurance systems May 24, 2014
Sandor Veres on autonomous agents May 23, 2014
Michael Fisher on verifying autonomous systems May 9, 2014
Kasper Stoy on self-reconfigurable robots May 2, 2014
MIRI’s May 2014 Newsletter May 1, 2014
Ruediger Schack on quantum Bayesianism April 29, 2014
David J. Atkinson on autonomous systems April 28, 2014
Help MIRI in a Massive 24-Hour Fundraiser on May 6th April 25, 2014
Dave Doty on algorithmic self-assembly April 23, 2014
Suzana Herculano-Houzel on cognitive ability and brain size April 22, 2014
Why MIRI? April 20, 2014
Thomas Bolander on self-reference and agent introspection April 13, 2014
Jonathan Millen on covert channel communication April 12, 2014
Wolf Kohn on hybrid systems control April 11, 2014
MIRI’s April 2014 Newsletter April 10, 2014
Will MacAskill on normative uncertainty April 8, 2014
Erik DeBenedictis on supercomputing April 3, 2014
2013 in Review: Fundraising April 2, 2014
Lyle Ungar on forecasting March 26, 2014
Randal Koene on whole brain emulation March 20, 2014
Max Tegmark on the mathematical universe March 19, 2014
MIRI’s March 2014 Newsletter March 18, 2014
Recent Hires at MIRI March 13, 2014
Toby Walsh on computational social choice March 10, 2014
Randall Larsen and Lynne Kidder on USA bio-response March 9, 2014
John Ridgway on safety-critical systems March 8, 2014
David Cook on the VV&A process March 7, 2014
Robert Constable on correct-by-construction programming March 2, 2014
The world’s distribution of computation (initial findings) February 28, 2014
Nik Weaver on Paradoxes of Rational Agency February 24, 2014
MIRI’s May 2014 Workshop February 22, 2014
Conversation with Holden Karnofsky about Future-Oriented Philanthropy February 21, 2014
2013 in Review: Friendly AI Research February 18, 2014
MIRI’s February 2014 Newsletter February 17, 2014
André Platzer on Verifying Cyber-Physical Systems February 15, 2014
Gerwin Klein on Formal Methods February 11, 2014
2013 in Review: Strategic and Expository Research February 8, 2014
MIRI’s Experience with Google Adwords February 6, 2014
Careers at MIRI February 3, 2014
Robust Cooperation: A Case Study in Friendly AI Research February 1, 2014
Two MIRI talks from AGI-11 January 31, 2014
Emil Vassev on Formal Verification January 30, 2014
How Big is the Field of Artificial Intelligence? (initial findings) January 28, 2014
Existential Risk Strategy Conversation with Holden Karnofsky January 27, 2014
2013 in Review: Outreach January 20, 2014
Want to help MIRI by investing in XRP? January 18, 2014
MIRI’s January 2014 Newsletter January 17, 2014
MIRI strategy conversation with Steinhardt, Karnofsky, and Amodei January 13, 2014
Kathleen Fisher on High-Assurance Systems January 10, 2014
Donor Story #1: Noticing Inferential Distance January 5, 2014
7 New Technical Reports, and a New Paper December 31, 2013
Winter 2013 Fundraiser Completed! December 26, 2013
Josef Urban on Machine Learning and Automated Reasoning December 21, 2013
2013 in Review: Operations December 20, 2013
New Paper: “Why We Need Friendly AI” December 18, 2013
MIRI’s December 2013 Newsletter December 16, 2013
Scott Aaronson on Philosophical Progress December 13, 2013
2013 Winter Matching Challenge December 2, 2013
New Paper: “Predicting AGI: What can we say when we know so little?” December 1, 2013
New Paper: “Racing to the Precipice” November 27, 2013
MIRI’s November 2013 Newsletter November 18, 2013
Support MIRI by Shopping at AmazonSmile November 6, 2013
Greg Morrisett on Secure and Reliable Systems November 5, 2013
From Philosophy to Math to Engineering November 4, 2013
Robin Hanson on Serious Futurism November 1, 2013
New Paper: “Embryo Selection for Cognitive Enhancement” October 30, 2013
Markus Schmidt on Risks from Novel Biotechnologies October 28, 2013
Bas Steunebrink on Self-Reflective Programming October 25, 2013
Probabilistic Metamathematics and the Definability of Truth October 23, 2013
Hadi Esmaeilzadeh on Dark Silicon October 21, 2013
Russell and Norvig on Friendly AI October 19, 2013
Richard Posner on AI Dangers October 18, 2013
MIRI’s October Newsletter October 12, 2013
Upcoming Talks at Harvard and MIT October 1, 2013
Paul Rosenbloom on Cognitive Architectures September 25, 2013
Effective Altruism and Flow-Through Effects September 14, 2013
How well will policy-makers handle AGI? (initial findings) September 12, 2013
MIRI’s September Newsletter September 10, 2013
Laurent Orseau on Artificial General Intelligence September 6, 2013
Five Theses, Using Only Simple Words September 5, 2013
How effectively can we plan for future decades? (initial findings) September 4, 2013
Stephen Hsu on Cognitive Genomics August 31, 2013
MIRI’s November 2013 Workshop in Oxford August 30, 2013
Transparency in Safety-Critical Systems August 25, 2013
2013 Summer Matching Challenge Completed! August 21, 2013
Luke at Quixey on Tuesday (Aug. 20th) August 16, 2013
August Newsletter: New Research and Expert Interviews August 13, 2013
What is AGI? August 11, 2013
“Algorithmic Progress in Six Domains” Released August 2, 2013
AI Risk and the Security Mindset July 31, 2013
Index of Transcripts July 25, 2013
MIRI’s December 2013 Workshop July 24, 2013
Nick Beckstead on the Importance of the Far Future July 17, 2013
Roman Yampolskiy on AI Safety Engineering July 15, 2013
James Miller on Unusual Incentives Facing AGI Companies July 12, 2013
MIRI’s July Newsletter: Fundraiser and New Papers July 11, 2013
2013 Summer Matching Challenge! July 8, 2013
What is Intelligence? June 19, 2013
MIRI’s July 2013 Workshop June 7, 2013
New Research Page and Two New Articles June 6, 2013
Friendly AI Research as Effective Altruism June 5, 2013
New Transcript: Yudkowsky and Aaronson May 29, 2013
When Will AI Be Created? May 15, 2013
AGI Impact Experts and Friendly AI Experts May 1, 2013
“Intelligence Explosion Microeconomics” Released April 29, 2013
“Singularity Hypotheses” Published April 25, 2013
Altair’s Timeless Decision Theory Paper Published April 19, 2013
MIRI’s Strategy for 2013 April 13, 2013
The Lean Nonprofit April 4, 2013
Early draft of naturalistic reflection paper March 22, 2013
March Newsletter March 7, 2013
Welcome to Intelligence.org February 28, 2013
We are now the “Machine Intelligence Research Institute” (MIRI) January 30, 2013
2012 Winter Matching Challenge a Success! January 20, 2013
December 2012 Newsletter December 19, 2012
2012 Winter Matching Challenge! December 6, 2012
November 2012 Newsletter November 7, 2012
September 2012 Newsletter September 21, 2012
August 2012 Newsletter August 21, 2012
July 2012 Newsletter August 6, 2012
2012 Summer Singularity Challenge Success! July 30, 2012
2012 Summer Singularity Challenge July 3, 2012
2011-2012 Winter Fundraiser Completed February 20, 2012
2011 Machine Intelligence Research Institute Winter Fundraiser December 27, 2011
Interview with New MIRI Research Fellow Luke Muehlhauser September 15, 2011
2011 Summer Matching Challenge Success! September 1, 2011
Machine Intelligence Research Institute Strategic Plan 2011 August 26, 2011
New Intelligence Explosion Website August 7, 2011
Announcing the $125,000 Summer Singularity Challenge July 22, 2011
Tallinn-Evans Challenge Grant Success! January 20, 2011
Announcing the Tallinn-Evans $125,000 Singularity Challenge December 21, 2010
2010 Singularity Research Challenge Fulfilled! March 1, 2010
Announcing the 2010 Singularity Research Challenge December 23, 2009
Introducing Myself February 16, 2009
Three Major Singularity Schools September 30, 2007
The Power of Intelligence July 10, 2007
Browse
Browse
Subscribe
Follow us on
