liveBook · Manning

Turing test

As explained in Sutskever's List

An evaluation in which a machine is judged intelligent if a human evaluator cannot reliably distinguish its text-based conversation from that of a human.

In his 1950 paper, Alan Turing replaced “Can machines think?” with a more practical question: can a machine converse well enough that a human interrogator cannot tell it from a person? This proposal became known as the Turing test, or imitation game. section 9.3.4

The test shifts attention from defining intelligence to judging observable performance. Turing offered it as a way to attribute intelligence in practice, not as a definition of intelligence itself. section 9.3.4

How Sutskever's List covers it

How deep it goes
Defines the test through text conversation and indistinguishability, while stopping short of defining intelligence itself.
Examples
Uses a human judge’s inability to reliably distinguish machine and human in text-only conversation as the test case.
What you can do after
Evaluate intelligence attribution through conversational performance without treating the result as a metaphysical definition.
How it connects
Connects intelligence, behaviorism, and the imitation game.
Cover of Sutskever's List
liveBookmanning.com
Read Sutskever's List on liveBook Get the book at manning.com

Also explained in

Compare how 2 books explain Turing test →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Sutskever's List. The section links point to the parts of the book it draws on.