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.

Control Problem Solution Before AGI

AI Progress Essay Contest

Question

From wikipedia "the AI control problem is the issue of how to build a superintelligent agent that will aid its creators, and avoid inadvertently building a superintelligence that will harm its creators... approaches to the control problem include alignment, which aims to align AI goal systems with human values, and capability control, which aims to reduce an AI system's capacity to harm humans or gain control."

Here is an introductory video.

Will the control problem be solved before the creation of "weak" Artificial General Intelligence?

The question will resolve as Yes if expert consensus is that the control problem is solved before the public demonstration of "weak" artificial general intelligence.

For the purposes of this question, "weak" AGI will be defined as meeting the qualifications in this question, the terms of which are reproduced in the fine print below.

A "weak" Artificial General Intelligence should be capable fo the following:

  • Able to reliably pass a Turing test of the type that would win the Loebner Silver Prize.

  • Able to score 90% or more on a robust version of the Winograd Schema Challenge, e.g. the "Winogrande" challenge or comparable data set for which human performance is at 90+%

  • Be able to score 75th percentile (as compared to the corresponding year's human students; this was a score of 600 in 2016) on all the full mathematics section of a circa-2015-2020 standard SAT exam, using just images of the exam pages and having less than ten SAT exams as part of the training data. (Training on other corpuses of math problems is fair game as long as they are arguably distinct from SAT exams.)

  • Be able to learn the classic Atari game "Montezuma's revenge" (based on just visual inputs and standard controls) and explore all 24 rooms based on the equivalent of less than 100 hours of real-time play (see closely-related question.)

By "unified" we mean that the system is integrated enough that it can, for example, explain its reasoning on an SAT problem or Winograd schema question, or verbally report its progress and identify objects during videogame play. (This is not really meant to be an additional capability of "introspection" so much as a provision that the system not simply be cobbled together as a set of sub-systems specialized to tasks like the above, but rather a single system applicable to many problems.)

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.