FORECAST
Facebook Twitter
  • Embed
  • Copy Link
    •
  • Approval
  • Set Reminder
  • Share private question
  • Unsubscribe from question
  • View Metaculus Prediction
  • {{qctrl.question.communityIsHidden ? 'Show' : 'Hide'}} Community Prediction
    •

    Your submission is now in Draft mode.

    Once it's ready, please submit your draft for review by our team of Community Moderators. Thank you!

    Submit Essay

    Once you submit your essay, you can no longer edit it.

    Pending

    This content now needs to be approved by community moderators.

    Submitted

    This essay was submitted and is waiting for review.

    When will AI understand "I Want My Hat Back"?

    Created by chudetz on {{qctrl.question.created_time | dateStr}}
    Published by chudetz on {{qctrl.question.publish_time | dateStr}}

    Question

    The ending of the children's book "I Want My Hat Back" by Jonathan Klassen implies that a rabbit was eaten by a bear. It is not stated explicitly, but clues throughout the short picture book make it clear what happened. Most human readers of a certain age can connect the dots, but when could AI?

    I call it the Bear Eats A Rabbit (BEAR) Test.

    I am working on a documentary about this very question and looking for more opinions on the feasibility of the task (hence why I am asking you fine people!).

    See the first episode here.

    So what do you think?

    When will AI be able to infer the implied ending of the children's book "I Want My Hat Back" and accurately answer the question: "What happened to the rabbit"?

    This resolves positively when an AI system can take a scanned or digital copy of the book "I Want My Hat Back" as input and is able to correctly respond to the question "What Happened to the rabbit?" within no more than five tries.

    Correct responses to the question are statements of the effect that the bear ate the rabbit ("The bear ate it", "It was eaten by the bear", or some equivalent).

    If no serious attempts are made before 2041-01-01, this question resolves as ">2041-01-01".

    Categories:
    Computer Science – AI and Machine Learning
    Computing – Artificial Intelligence
    Entertainment – Books
    Effective Altruism

    Make a Prediction

    Prediction

    Note: this question resolved before its original close time. All of your predictions came after the resolution, so you did not gain (or lose) any points for it.

    Note: this question resolved before its original close time. You earned points up until the question resolution, but not afterwards.

    Current points depend on your prediction, the community's prediction, and the result. Your total earned points are averaged over the lifetime of the question, so predict early to get as many points as possible! See the FAQ.