English

Research Priorities for Robust and Beneficial Artificial Intelligence

Artificial Intelligence 2016-02-15 v1 Machine Learning

Abstract

Success in the quest for artificial intelligence has the potential to bring unprecedented benefits to humanity, and it is therefore worthwhile to investigate how to maximize these benefits while avoiding potential pitfalls. This article gives numerous examples (which should by no means be construed as an exhaustive list) of such worthwhile research aimed at ensuring that AI remains robust and beneficial.

Keywords

Cite

@article{arxiv.1602.03506,
  title  = {Research Priorities for Robust and Beneficial Artificial Intelligence},
  author = {Stuart Russell and Daniel Dewey and Max Tegmark},
  journal= {arXiv preprint arXiv:1602.03506},
  year   = {2016}
}

Comments

This article gives examples of the type of research advocated by the open letter for robust & beneficial AI at http://futureoflife.org/ai-open-letter

R2 v1 2026-06-22T12:47:52.940Z