AI Safety Research

Bart Selman

Professor, Department of Computer Science

Cornell University

bart.selman@gmail.com

Project: Scaling-up AI Systems: Insights From Computational Complexity

Amount Recommended:    $24,950

Project Summary

There is general consensus within the AI research community that progress in the field is accelerating: it is believed that human-level AI will be reached within the next one or two decades. A key question is whether these advances will accelerate further after general human level AI is achieved, and, if so, how rapidly the next level of AI systems (?super-human?) will be achieved.

Since the mid 1970s, Computer scientists have developed a rich theory about the computational resources that are needed to solve a wide range of problems. We will use these methods to make predictions about the feasibility of super-human level cognition.

Technical Abstract

There is general consensus within the AI research community that progress in the field is accelerating: it is believed that human-level AI will be reached within the next one or two decades on a range of cognitive tasks. A key question is whether these advances will accelerate further after general human level AI is achieved, and, if so, how rapidly the next level of AI systems (‘super-human’) will be achieved. Having a better understanding of how rapidly we may reach this next phase will be useful in preparing for the advent of such systems.

Computational complexity theory provides key insights into the scalability of computational systems. We will use methods from complexity theory to analyze the possibility of the scale-up to super-human intelligence and the speed of such scale-up for different categories of cognition.

Workshops

  1. The Future of Artificial Intelligence: New York University, NY.
  2. Control and Responsible Innovation in the Development of Autonomous Systems Workshop: April 24-26, 2016. The Hastings Center, Garrison, NY.
    • The four co-­chairs (Gary Marchant, Stuart Russell, Bart Selman, and Wendell Wallach) and The Hastings Center staff (particularly Mildred Solomon and Greg Kaebnick) designed this first workshop
    • This workshop was focused on exposing participants to relevant research progressing in an array of fields, stimulating extended reflection upon key issues and beginning a process of dismantling intellectual silos and loosely knitting the represented disciplines into a transdisciplinary community. Twenty-five participants gathered at The Hastings Center in Garrison, NY from April 24th – 26th, 2016.
    • The workshop included representatives from key institutions that have entered this space, including IEEE, the Office of Naval Research, the World Economic Forum, and of course AAAI.
    • They are planning a second workshop, scheduled for October 30-November 1, 2016
  3. Colloquium Series on Robust and Beneficial AI (CSRBAI):  May 27-June 17, 2016. MIRI, Berkeley, CA.
    • Selman participated in this 22-day June colloquium series (https://intelligence.org/colloquium-series/) with the Future of Humanity Institute, which included four additional workshops.
    • Specific Workshop: “Robustness and Error-Tolerance.” June 4-5.
      • How can humans ensure that when AI system fail, they fail gracefully and detectably? This is difficult for systems that must adapt to new or changing environments; standard PAC guarantees for machine learning systems fail to hold when the distribution of test data does not match the distribution of training data. Moreover, systems capable of means-end reasoning may have incentives to conceal failures that would result in their being shut down. Researchers would much prefer to have methods of developing and validating AI systems such that any mistakes can be quickly noticed and corrected.