Corpus ID: 210920551

Artificial Intelligence, Values and Alignment

@article{Gabriel2020ArtificialIV,
  title={Artificial Intelligence, Values and Alignment},
  author={Iason Gabriel},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.09768}
}
  • Iason Gabriel
  • Published in ArXiv 2020
  • Computer Science
  • This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are interrelated, creating space for productive engagement between people working in both domains. Second, it is important to be clear about the goal of alignment. There are significant differences between AI that aligns with instructions, intentions, revealed preferences, ideal preferences, interests and values… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 51 REFERENCES

    AGI Safety Literature Review

    VIEW 1 EXCERPT

    De novo structure prediction with deeplearning based scoring

    • H Penedones
    • Democratic authority : A philosophical framework
    • 2018

    Occam’s razor is insufficient to infer the preferences of irrational agents, in ‘Advances in Neural Information

    • S. Armstrong, S. Mindermann
    • Processing Systems’,
    • 2018
    VIEW 1 EXCERPT

    Social choice and the value alignment problem, in ‘Artificial Intelligence Safety

    • M. william-macaskill Prasad
    • 2018

    The Moral Machine experiment