The Meta-Turing Test

TL;DR

The paper introduces a symmetric meta-Turing test where humans and machines evaluate each other, aiming to improve robustness against deception compared to the original Turing test.

Contribution

It proposes a novel, reciprocal testing framework that enhances the robustness of evaluating machine intelligence over the traditional imitation game.

Findings

The meta-Turing test reduces susceptibility to simple deception.

Refinements improve the test's robustness and applicability.

The approach can be adapted to enhance the original Turing test.

Abstract

We propose an alternative to the Turing test that removes the inherent asymmetry between humans and machines in Turing's original imitation game. In this new test, both humans and machines judge each other. We argue that this makes the test more robust against simple deceptions. We also propose a small number of refinements to improve further the test. These refinements could be applied also to Turing's original imitation game.