MIRI has two papers forthcoming in the conference proceedings of AGI-15. The first paper, previously released as a MIRI technical report, is “Reflective variants of Solomonoff induction and AIXI,” by Benja Fallenstein, Nate Soares, and Jessica Taylor. The second paper, “Two Attempts to Formalize Counterpossible Reasoning in Deterministic Settings,” by Nate Soares and Benja Fallenstein, is a… Read more »
Posts By: Luke Muehlhauser
MIRI-related talks from the decision theory conference at Cambridge University
Recently, MIRI co-organized a conference at Cambridge University titled Self-prediction in decision theory and artificial intelligence. At least six of the conference’s talks directly discussed issues raised in MIRI’s technical agenda: MIRI research fellow (and soon, Executive Director) Nate Soares gave a talk titled “What is a what if?” (.pdf w/o notes, .pptx w/ notes), on theories of… Read more »
A fond farewell and a new Executive Director
Dear friends and supporters of MIRI, I have some important news to share with you about the future of MIRI. Given my passion for doing research, I’m excited to have accepted a research position at GiveWell. Like MIRI, GiveWell is an excellent cultural fit for me, and I believe they’re doing important work. I look… Read more »
New papers on reflective oracles and agents
We recently released two new papers on reflective oracles and agents. The first is “Reflective oracles: A foundation for classical game theory,” by Benja Fallenstein, Jessica Taylor, and Paul Christiano. Abstract: Classical game theory treats players as special—a description of a game contains a full, explicit enumeration of all players—even though in the real world, “players” are… Read more »
Recent AI control brainstorming by Stuart Armstrong
MIRI recently sponsored Oxford researcher Stuart Armstrong to take a solitary retreat and brainstorm new ideas for AI control. This brainstorming generated 16 new control ideas, of varying usefulness and polish. During the past month, he has described each new idea, and linked those descriptions from his index post: New(ish) AI control ideas. He also named each… Read more »
2014 in review
It’s time for my review of MIRI in 2014. A post about our next strategic plan will follow in the next couple months, and I’ve included some details about ongoing projects at the end of this review. 2014 Summary Since early 2013, MIRI’s core goal has been to help create a new field of research devoted to the technical challenges… Read more »
New report: “An Introduction to Löb’s Theorem in MIRI Research”
Today we publicly release a new technical report by Patrick LaVictoire, titled “An Introduction to Löb’s Theorem in MIRI Research.” The report’s introduction begins: This expository note is devoted to answering the following question: why do many MIRI research papers cite a 1955 theorem of Martin Löb, and indeed, why does MIRI focus so heavily… Read more »
Introducing the Intelligent Agent Foundations Forum
Today we are proud to publicly launch the Intelligent Agent Foundations Forum (RSS), a forum devoted to technical discussion of the research problems outlined in MIRI’s technical agenda overview, along with similar research problems. Patrick’s welcome post explains: Broadly speaking, the topics of this forum concern the difficulties of value alignment- the problem of how to ensure that… Read more »
