New paper: “Formalizing convergent instrumental goals”

Posted by & filed under Papers.

Tsvi Benson-Tilsen, a MIRI associate and UC Berkeley PhD candidate, has written a paper with contributions from MIRI Executive Director Nate Soares on strategies that will tend to be useful for most possible ends: “Formalizing convergent instrumental goals.” The paper will be presented as a poster at the AAAI-16 AI, Ethics and Society workshop. Steve… Read more »

November 2015 Newsletter

Posted by & filed under Newsletters.

Research updates A new paper: Leó Szilárd and the Danger of Nuclear Weapons New at IAFF: Subsequence Induction A shortened version of the Reflective Oracles paper has been published in the LORI 2015 conference proceedings. General updates Castify has released professionally recorded audio versions of Eliezer Yudkowsky’s Rationality: From AI to Zombies: Part 1, Part… Read more » contributors discuss the future of AI

Posted by & filed under News.

In January, nearly 200 public intellectuals submitted essays in response to the 2015 question, “What Do You Think About Machines That Think?” (available online). The essay prompt began: In recent years, the 1980s-era philosophical discussions about artificial intelligence (AI)—whether computers can “really” think, refer, be conscious, and so on—have led to new conversations about… Read more »

October 2015 Newsletter

Posted by & filed under Newsletters.

Research updates New paper: Asymptotic Logical Uncertainty and The Benford Test New at IAFF: Proof Length and Logical Counterfactuals Revisited; Quantilizers Maximize Expected Utility Subject to a Conservative Cost Constraint General updates As a way to engage more researchers in mathematics, logic, and the methodology of science, Andrew Critch and Tsvi Benson-Tilsen are currently co-running… Read more »

New paper: “Asymptotic logical uncertainty and the Benford test”

Posted by & filed under Papers.

We have released a new paper on logical uncertainty, co-authored by Scott Garrabrant, Siddharth Bhaskar, Abram Demski, Joanna Garrabrant, George Koleszarik, and Evan Lloyd: “Asymptotic logical uncertainty and the Benford test.” Garrabrant gives some background on his approach to logical uncertainty on the Intelligent Agent Foundations Forum: The main goal of logical uncertainty is to… Read more »

September 2015 Newsletter

Posted by & filed under Newsletters.

Research updates New analyses: When AI Accelerates AI; Powerful Planners, Not Sentient Software New at AI Impacts: Research Bounties; AI Timelines and Strategies New at IAFF: Uniform Coherence 2; The Two-Update Problem Andrew Critch, a CFAR cofounder, mathematician, and former Jane Street trader, joined MIRI as our fifth research fellow this month! As a result… Read more »

AI and Effective Altruism

Posted by & filed under Analysis.

MIRI is a research nonprofit specializing in a poorly-explored set of problems in theoretical computer science. GiveDirectly is a cash transfer service that gives money to poor households in East Africa. What kind of conference would bring together representatives from such disparate organizations — alongside policy analysts, philanthropists, philosophers, and many more? Effective Altruism Global,… Read more »