# What is the Turing test?

Artificial Intelligence Asked on August 24, 2021

I’m looking for intuition in simple words but also some simple insights (I don’t know if the latter is possible). Can anybody shed some light on the Turing test?

The Turing test is a test proposed by Alan Turing (one of the founders of computer science and artificial intelligence), described in section 1 of paper Computing Machinery and Intelligence (1950), to answer the question

Can machines think?

More precisely, the Turing test was originally framed as an interactive quiz (denoted as the imitation game by Turing) where a human interrogator $$C$$ asks multiple questions to two entities, $$A$$ (a computer) and $$B$$ (a human), which stay in different rooms than the room of the interrogator, so the interrogator cannot see them, in order to figure out which one is $$A$$ (the computer) and which one is $$B$$ (the human). $$A$$ and $$B$$ can only communicate in written form or any form that avoids them being easily recognized by $$C$$. The goal of the computer is to fool the interrogator and make him/her believe that it is a human and the goal of $$B$$ is to somehow help him and make him believe that he/she is the actual human.

If the computer is able to fool the interrogator and make him/her believe that it is a human, then that would be an indication that machines can think. However, note that even Turing called this game the imitation game, so Turing was aware of the fact that this game would only really show that a machine can imitate a human (unless he was using the term "imitation" differently than its current meaning).

Nowadays, there are different variations of the Turing test and some people use the term Turing test to refer to any test that attempts to tell humans and computers apart. For example, some people consider the CAPTCHA test a Turing test. In fact, CAPTCHA stands for "Completely Automated Public Turing Test To Tell Computers and Humans Apart".

The Turing test also has different interpretations and meanings. Some people think that the Turing test is sufficient to test that a machine can actually think and possesses consciousness, other people think that this only tests human-like intelligence (and there could be other intelligences) and some people (like me) think that this test is limited and only tests the conversational skills (and maybe other properties too) of the machine. Even Turing attempted to address these issues in the same paper (section 2), where he discusses some advantages and disadvantages of his imitation game. In any case, we can all agree that, if machines (in particular, programs like Siri, Google Home, Cortana, or Alexa) were always able to pass the Turing test, they would be a lot more useful, interesting and entertaining than they are now.

Correct answer by nbro on August 24, 2021

According to Wikipedia

The "standard interpretation" of the Turing test, in which player C, the interrogator, is given the task of trying to determine which player – A or B – is a computer and which is a human. The interrogator is limited to using the responses to written questions to make the determination.

Answered by estamos on August 24, 2021

## Related Questions

### Is A* with an admissible but inconsistent heuristic optimal?

1  Asked on August 24, 2021 by harry-stuart

### Is there a way to get landmark features automatically learned by a neural network?

1  Asked on August 24, 2021 by user784446

1  Asked on August 24, 2021 by nathan-b

### NEAT can’t solve XOR completely

0  Asked on August 24, 2021 by creepsy

### Why is GPT-3 such a game changer?

1  Asked on August 24, 2021 by parzival

### How can the FCNN reduce the dimensions of the input from $1048 times 100$ to $523 times 100$ with max-pooling?

0  Asked on August 24, 2021

### Are there examples of agents that use a more modest number of parameters on Pendulum (or similar environments)?

1  Asked on August 24, 2021

### How can one be sure that a particular neural network architecture would work?

0  Asked on August 24, 2021 by naveen-reddy-marthala

### How do we make our outputs to have the same size as the true mask?

1  Asked on August 24, 2021 by ravi-teja

### Is it common to have extreme policy’s probabilities?

1  Asked on August 24, 2021 by curiouscat22

### How AlphaGo Zero is learning from $pi_t$ when $z_t = -1$?

1  Asked on August 24, 2021

### Can we use imitation learning for on-policy algorithms?

0  Asked on February 27, 2021 by khush-agrawal

### Why am I getting a difference between training accuracy and accuracy calculated with Keras’ predict_classes on a subset of the training data?

1  Asked on February 23, 2021 by saha

### Can transformer be better than RNN for online speech recognition?

1  Asked on February 23, 2021

### In the case of invalid actions, which output probability matrix should we use in back-propagation?

1  Asked on February 20, 2021 by guineu

### Multi class text classification when having only one sample for classes

1  Asked on February 19, 2021 by fara

### How to identify segment/object that is anomaly using computer vision

0  Asked on February 14, 2021 by tyler-h

### What sort of game problems can neural networks trained/evolved with evolutionary algorithms solve, and how are they typically implemented?

3  Asked on February 13, 2021 by neomerarcana

### How are IOUs for ground truth boxes in YOLO calculated?

1  Asked on February 12, 2021 by nivter

### How to design a good evaluation function for a go-like game?

1  Asked on February 11, 2021 by nae