the open
    research
    Contribute
    Back to the reading lists

    Safety, alignment & interpretability· 2018

    AI safety via debate

    Geoffrey Irving (first author) · 2018

    Read the original

    arXiv 1805.00899OpenAlex W2798877128

    On the reading lists

    Why it matters

    Proposed adversarial debate between AI agents to help humans supervise complex decisions.

    Condensed from the expert lists' notes.

    The record

    First released
    2018 (from arXiv 1805.00899)
    Citations
    496 citations, as counted by Papers With Code (CC BY-SA 4.0)
    Named by
    both expert lists
    Score
    0.284 · computed rank 643 · consensus 0.52, must-read 0.5, citations percentile 0.223 (2010s · safety), awards 0, existing lists 0. Method

    Data sources

    Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.