Stanford
University
  • Stanford Home
  • Maps & Directions
  • Search Stanford
  • Emergency Info
  • Terms of Use
  • Privacy
  • Copyright
  • Trademarks
  • Non-Discrimination
  • Accessibility
© Stanford University.  Stanford, California 94305.
HAI Weekly Seminar with Kate Vredenburgh - Against Rationale Explanations | Stanford HAI
Skip to content
  • About

    • About
    • People
    • Get Involved with HAI
    • Support HAI
    • Subscribe to Email
  • Research

    • Research
    • Research Programs
    • Grants
    • Marlowe (opens in new tab)
    • Student Affinity Groups
    • Centers & Labs
    • Research Publications
    • Research Partners
  • Education

    • Education
    • Executive and Professional Education
    • Government and Policymakers
    • K-12
    • Stanford Students
  • Policy

    • Policy
    • Policy Publications
    • Policymaker Education
    • Student Opportunities
  • AI Index

    • AI Index
    • AI Index Report
    • Global Vibrancy Tool
    • People
  • News
  • Events
  • Industry
  • Centers & Labs
Navigate
  • About
  • Events
  • AI Glossary
  • Careers
  • Search
Participate
  • Get Involved
  • Support HAI
  • Contact Us

Stay Up To Date

Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.

Sign Up For Latest News

Your browser does not support the video tag.
eventSeminar

HAI Weekly Seminar with Kate Vredenburgh - Against Rationale Explanations

Status
Past
Date
Friday, May 15, 2020 11:00 AM - 12:00 PM PST/PDT
Topics
Foundation Models
Sciences (Social, Health, Biological, Physical)
Share
Link copied to clipboard!

Related Events

AI100 | AI Goes Mainstream: The Scaling Era and the Rise of Generative AI
SeminarNov 18, 202612:00 PM - 1:15 PM
November
18
2026

This talk will cover key insights from the third AI100 report, AI Goes Mainstream: The Scaling Era and the Rise of Generative AI, set for release in November 2026. The report was commissioned by the AI100 standing committee and led by study panel chair Michael Wooldridge.

Seminar

AI100 | AI Goes Mainstream: The Scaling Era and the Rise of Generative AI

Nov 18, 202612:00 PM - 1:15 PM

This talk will cover key insights from the third AI100 report, AI Goes Mainstream: The Scaling Era and the Rise of Generative AI, set for release in November 2026. The report was commissioned by the AI100 standing committee and led by study panel chair Michael Wooldridge.

Christopher Ong | Research Acceleration: The View Inside OpenAI
Nov 16, 202612:00 PM - 1:00 PM
November
16
2026

In the last year, AI models have rapidly improved on public benchmarks measuring their ability to carry out research tasks autonomously. Such performance suggests that models may be capable of automating parts of the AI R&D process itself, thereby accelerating the pace of AI progress.

Event

Christopher Ong | Research Acceleration: The View Inside OpenAI

Nov 16, 202612:00 PM - 1:00 PM

In the last year, AI models have rapidly improved on public benchmarks measuring their ability to carry out research tasks autonomously. Such performance suggests that models may be capable of automating parts of the AI R&D process itself, thereby accelerating the pace of AI progress.

"In this talk, I will argue against one popular socio-technical solution to the problem of opacity: rationale explanations. Such explanations are taken to achieve many important political values enabled by explanations, such as trust, recourse, respect, and accountability, as well as to enable decision-makers to comply with GDPR. For example, by providing data subjects with a single or small set of counterfactuals that link specific inputs to a desired output value, rationale explanations based on counterfactuals enable individuals to achieve recourse. However, I argue that rationale explanations are often not the best means to enable the relevant political values. The general insight is that rationale based explanations combine two different types of politically important explanations: causal explanations, that give individuals the information needed to adjust their behavior, and normative explanations, which justify the use of the system or a particular application of it." - Kate Vredenburgh

Watch Event Recording

Speaker
Kate Vredenburgh
HAI-EIS Postdoctoral Fellow