Asymptotically Unambitious Artificial General Intelligence

Authors

  • Michael Cohen Oxford University
  • Badri Vellambi University of Cincinnati
  • Marcus Hutter Australian National University

DOI:

https://doi.org/10.1609/aaai.v34i03.5628

Abstract

General intelligence, the ability to solve arbitrary solvable problems, is supposed by many to be artificially constructible. Narrow intelligence, the ability to solve a given particularly difficult problem, has seen impressive recent development. Notable examples include self-driving cars, Go engines, image classifiers, and translators. Artificial General Intelligence (AGI) presents dangers that narrow intelligence does not: if something smarter than us across every domain were indifferent to our concerns, it would be an existential threat to humanity, just as we threaten many species despite no ill will. Even the theory of how to maintain the alignment of an AGI's goals with our own has proven highly elusive. We present the first algorithm we are aware of for asymptotically unambitious AGI, where “unambitiousness” includes not seeking arbitrary power. Thus, we identify an exception to the Instrumental Convergence Thesis, which is roughly that by default, an AGI would seek power, including over us.

Downloads

Published

2020-04-03

How to Cite

Cohen, M., Vellambi, B., & Hutter, M. (2020). Asymptotically Unambitious Artificial General Intelligence. Proceedings of the AAAI Conference on Artificial Intelligence, 34(03), 2467-2476. https://doi.org/10.1609/aaai.v34i03.5628

Issue

Section

AAAI Technical Track: Human-AI Collaboration