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

    Will an AI successfully masquerade as human for 20 questions by 2017?

    Created by Anthony on {{qctrl.question.created_time | dateStr}}.

    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!

    Question

    The Turing Test (aka the "Imitation Game") is a well-known thought experiment as well as an actual test that can be done on computer programs that converse via text. The idea is simple: a human judge converses with the machine, and if it cannot discern the machine from a human conversant, then the machine has "passed."

    No conversing system (or "Chatbot") has passed the Turing test (despite some reports), but they are getting better. Each year there is an annual competition in artificial intelligence for the Loebner Prize, which awards a bronze-level prize to the most human chatbox, and offers a silver- and gold-level prizes for actually passing versions of the full Turing test.

    To qualify for the conversation test, chatbot contestants answer 20 open-ended questions designed by a panel. The questions are new each year, and the same questions offered to each chatbot. You can see the 2014 and 2015 questions here, along with the answers that each of 15-20 chatbots gave.

    Some of the chatbots give pretty convincing answers to many of the questions, scoring as much as 89% in the contest's scoring system. Examination suggests a typical human would easily score 100% most of the time.

    As a step toward passing a full Turing test, in the 2016 or 2017 competitions, will a chatbot score 100% in the 20-question preliminary round?

    Categories:
    Technological Advances
    Computer Science – AI and Machine Learning
    Computing – Artificial Intelligence

    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.

    This question is not yet open for predictions.

    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.

    Metaculus help: Predicting

    Predictions are the heart of Metaculus. Predicting is how you contribute to the wisdom of the crowd, and how you earn points and build up your personal Metaculus track record.

    The basics of predicting are very simple: move the slider to best match the likelihood of the outcome, and click predict. You can predict as often as you want, and you're encouraged to change your mind when new information becomes available.

    The displayed score is split into current points and total points. Current points show how much your prediction is worth now, whereas total points show the combined worth of all of your predictions over the lifetime of the question. The scoring details are available on the FAQ.

    Thanks for predicting!

    Your prediction has been recorded anonymously.

    Want to track your predictions, earn points, and hone your forecasting skills? Create an account today!

    Track your predictions
    Continue exploring the site
    random question question list