From September 7-13, MIRI will host its 4th Workshop on Logic, Probability, and Reflection. The focus of this workshop will be the foundations of decision theory. Participants confirmed so far include: Paul Christiano (UC Berkeley) Wei Dai (independent) Gary Drescher (independent) Kenny Easwaran (USC) Cameron Freer (MIT) Patrick LaVictoire (Quixey) Ilya Shpitser (U Southampton) Vladimir Slepnev… Read more »
Posts By: Luke Muehlhauser
Responses to Catastrophic AGI Risk: A Survey
MIRI is self-publishing another technical report that was too lengthy (60 pages) for publication in a journal: Responses to Catastrophic AGI Risk: A Survey. The report, co-authored by past MIRI researcher Kaj Sotala and University of Louisville’s Roman Yampolskiy, is a summary of the extant literature (250+ references) on AGI risk, and can serve either as a guide… Read more »
What is Intelligence?
When asked their opinions about “human-level artificial intelligence” — aka “artificial general intelligence” (AGI) — many experts understandably reply that these terms haven’t yet been precisely defined, and it’s hard to talk about something that hasn’t been defined. In this post, I want to briefly outline an imprecise but useful “working definition” for intelligence we… Read more »
MIRI’s July 2013 Workshop
From July 8-14, MIRI will host its 3rd Workshop on Logic, Probability, and Reflection. The focus of this workshop will be the Löbian obstacle to self-modifying systems. Participants confirmed so far include: Andrew Critch (just finished his math PhD at UC Berkeley, now working at CFAR) Abram Demski (USC) Benja Fallenstein (Bristol U) Marcello Herreshoff (Google)… Read more »
New Research Page and Two New Articles
Our new Research page has launched! Our previous research page was a simple list of articles, but the new page describes the purpose of our research, explains four categories of research to which we contribute, and highlights the papers we think are most important to read. We’ve also released drafts of two new research articles…. Read more »
Friendly AI Research as Effective Altruism
MIRI was founded in 2000 on the premise that creating Friendly AI might be a particularly efficient way to do as much good as possible. Some developments since then include: The field of “effective altruism” — trying not just to do good but to do as much good as possible — has seen more publicity… Read more »
New Transcript: Yudkowsky and Aaronson
In When Will AI Be Created?, I referred to a bloggingheads.tv conversation between Eliezer Yudkowsky and Scott Aaronson. A transcript of that dialogue is now available, thanks to MIRI volunteers Ethan Dickinson, Daniel Kokotajlo, and Rick Schwall. See also the transcript for a bloggingheads.tv conversation between Eliezer Yudkowsky and Massimo Pigliucci. To join these volunteers in assisting… Read more »
Sign up for DAGGRE to improve science & technology forecasting
In When Will AI Be Created?, I named four methods that might improve our forecasts of AI and other important technologies. Two of these methods were explicit quantification and leveraging aggregation, as exemplified by IARPA’s ACE program, which aims to “dramatically enhance the accuracy, precision, and timeliness of… forecasts for a broad range of event types, through… Read more »