Research Priorities for Robust and Beneficial Artificial Intelligence

@article{Russell2015ResearchPF,
  title={Research Priorities for Robust and Beneficial Artificial Intelligence},
  author={S. Russell and D. Dewey and Max Tegmark},
  journal={AI Mag.},
  year={2015},
  volume={36},
  pages={105-114}
}
  • S. Russell, D. Dewey, Max Tegmark
  • Published 2015
  • Computer Science, Engineering
  • AI Mag.
  • 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. 

    Topics from this paper.

    BEYOND MAD ? : THE RACE FOR ARTIFICIAL GENERAL INTELLIGENCE
    • 8
    • PDF
    Artificial Intelligence : Global Risk and Long Term Strategy for Ending Fast Take off
    • 1
    • PDF
    On the promotion of safe and socially beneficial artificial intelligence
    • 30
    • Highly Influenced
    • PDF
    Using Stories to Teach Human Values to Artificial Agents
    • 47
    • PDF
    AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
    • 24
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 178 REFERENCES
    Friendly Artificial Intelligence: The Physics Challenge
    • 6
    • PDF
    Artificial Intelligence : A Modern Approach
    • 23,451
    • PDF
    Artificial Intelligence, Employment, and Income
    • 28
    • PDF
    Avoiding Unintended AI Behaviors
    • 18
    • PDF
    The Singularity: a Philosophical Analysis
    • 243
    • PDF
    The First Law of Robotics (A Call to Arms)
    • 118
    • PDF
    Provably Bounded Optimal Agents
    • 256
    • PDF
    Agents, Bodies, Constraints, Dynamics, and Evolution
    • 10
    • PDF