BIROn - Birkbeck Institutional Research Online

    Real sparks of Artificial Intelligence and the importance of inner interpretability

    Grzankowski, Alex (2024) Real sparks of Artificial Intelligence and the importance of inner interpretability. Inquiry: An interdisciplinary journal of philosophy , ISSN 0020-174X.

    [img] Text
    52672.pdf - Author's Accepted Manuscript
    Restricted to Repository staff only

    Download (4MB)
    [img]
    Preview
    Text
    52672a.pdf - Published Version of Record
    Available under License Creative Commons Attribution Non-commercial No Derivatives.

    Download (3MB) | Preview

    Abstract

    The present paper looks at one of the most thorough articles on the intelligence of GPT, research conducted by engineers at Microsoft. Although there is a great deal of value in their work, I will argue that, for familiar philosophical reasons, their methodology, ‘Black-box Interpretability’ is wrongheaded. But there is a better way. There is an exciting and emerging discipline of ‘Inner Interpretability’ (and specifically Mechanistic Interpretability) that aims to uncover the internal activations and weights of models in order to understand what they represent and the algorithms they implement. In my view, a crucial mistake in Black-box Interpretability is the failure to appreciate that how processes are carried out matters when it comes to intelligence and understanding. I can’t pretend to have a full story that provides both necessary and sufficient conditions for being intelligent, but I do think that Inner Interpretability dovetails nicely with plausible philosophical views of what intelligence requires. So the conclusion is modest, but the important point in my view is seeing how to get the research on the right track. Towards the end of the paper, I will show how some of the philosophical concepts can be used to further refine how Inner Interpretability is approached, so the paper helps draw out a profitable, future two-way exchange between Philosophers and Computer Scientists.

    Metadata

    Item Type: Article
    School: Birkbeck Faculties and Schools > Faculty of Humanities and Social Sciences > School of Historical Studies
    Depositing User: Alex Grzankowski
    Date Deposited: 08 Jan 2024 14:53
    Last Modified: 29 Jan 2024 00:35
    URI: https://eprints.bbk.ac.uk/id/eprint/52672

    Statistics

    Activity Overview
    6 month trend
    10Downloads
    6 month trend
    83Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item