When will the first artificial intelligence be created?

2024 Author: Malcolm Clapton | [email protected]. Last modified: 2023-12-17 03:44

They say that artificial intelligence has been working in the bowels of military laboratories since 2007. It is possible that there are already results. It is no coincidence that just a month ago, Elon Musk announced support for countering artificial intelligence technologies and invested $ 7 million in research in this area.

“There is a risk that something really dangerous will happen in the next five years. Ten years at the most,”said the entrepreneur in a discussion on edge.org.

If machines are programmed to self-improve recursively, their functions can be detrimental to us. For example, if the machine's job is to get rid of email spam, it may decide that it is much easier to get rid of people.

Elon Musk founder of Tesla and SpaceX

Solidarity with Musk and Steve Wozniak, who believes that "artificial intelligence will one day become smart enough to get rid of a person." Bill Gates is sure that if you do not control the creation of AI, then "artificial intelligence will evolve into a state that conflicts with the goals of human systems." And finally, the famous astrophysicist Stephen Hawking bluntly stated that "artificial intelligence can end the existence of mankind."

Together with Elon Musk, Hawking posted an open letter on the website urging the scientific community to be attentive to the progress of their research in the field of artificial intelligence. However, among the signatories there are no names of Sergey Brin and Larry Page. And this is no coincidence. Most recently, Google announced the creation of a new AI built on conversation simulation.

Here's a snippet of a conversation between a man and a Google Machine:

H: What is the meaning of life?

M.: Do good.

H: What are we living for?

M.: To live forever.

H: What is the meaning of existence?

M: To find out what will happen when we reach planet Earth.

H: Where are you now?

M.: In the center of emptiness.

H: What is the meaning of death?

M.: To get life.

H: What is the meaning of reason?

M.: In order to understand what it is.

H: What is the meaning of feelings?

M: I don't know.

Quite a meaningful conversation. “This is a starting point, a kind of pivot for the future of artificial intelligence,” says Evgeniy Karyuk, Executive Director of Biplan. “Already today we can assume that by 2030 we will see quite real prototypes endowed with artificial intelligence, albeit at an initial stage.”

The full content of all human and Google Machine conversations can be viewed. There, for comparison, conversations of a person and are given. Cleverbot is a web application that uses artificial intelligence algorithms to communicate with a person. It was invented in 1988 by the scientist Rollo Carpenter. Throughout its existence, Cleverbot has conducted over 65 million conversations with people. In 2011, Cleverbot showed 51% on the Turing test.

The Turing test is an empirical test, the idea of which was proposed by Alan Turing in the article "Computing Machines and the Mind", published in 1950 in the philosophical journal Mind. The purpose of the test is to find out if the computer can think.

And here is my conversation with Cleverbot:

Man: What is the meaning of life?

Cleverbot: There is no sense in life.

Man: What are we living for?

Cleverbot: Well, we live for someone else, and if you are single, there is no need to live.

Human: What is the meaning of existence?

Cleverbot: I have my own answer to this question.

Human: Where are you now?

Cleverbot: In Moscow.

Man: What is the meaning of death?

Cleverbot: I want to ask you this.

Human: What is the meaning of reason?

Cleverbot: I have my own answer to this question.

Man: What is the meaning of feelings?

Cleverbot: Why I was born.

Obviously, the Google Engine provides much more meaningful answers. Cleverbot substitutes phrases of other people that are suitable, in its opinion. Sometimes it really seems that the other person is answering, but nothing more.

There is another point of view, according to which artificial intelligence is impossible in principle. Incompleteness is often cited as the main argument. The bottom line is that a person is able to solve algorithmically insoluble problems, but a computer is not. “By the age of three, a child confidently solves the problem, ripe fruit or not, due to the fact that he has neural connections, with the help of which he can answer the question of ripeness: color, taste, smell, softness or hardness,” says Evgeny Pluzhnik. First Vice-Rector of the Moscow Technological Institute. - Is the machine capable of learning this? I am sure yes! If she has a large database of images, she can measure the fructose content and determine the softness of the fruit. But what happens if the machine is slipped with a sponge painted blue and soaked in sweet water? Is the machine capable of real understanding at this moment?"

"A modern computer can easily cope with any complex activity, be it chess or mathematical calculations, but only if this activity can be described using clear computational rules," - said the famous mathematician Roger Penrose in one of his lectures. “Artificial intelligence is the ability of a system to create, during self-learning, programs capable of solving problems of a certain class of complexity,” says Yevgeny Pluzhnik. "I am confident that in the next 100 years we will not witness the emergence of strong artificial intelligence."

And finally, one more question for Cleverbot.

Human: There was 1 apple, 1 tomato, 1 cucumber, and 1 pear. How many fruits are there in total?

Cleverbot: Ten o'clock in the evening.