Is Artificial Intelligence the Reason We Are Ended?
What is artificial intelligence and what are people really afraid of?
In contact with
Classmates
Artificial intelligence is a topic about which everyone has formed their own opinion.
Experts on this issue are divided into two camps.
The first believes that artificial intelligence does not exist, the second believes that it does exist.
Rusbase found out which of them is right.
Artificial intelligence and the negative consequences of imitation
The main reason for the debate about artificial intelligence is the understanding of the term. The stumbling block was the very concept of intelligence and... ants. People who deny the existence of AI rely on the fact that it is impossible to create artificial intelligence, because human intelligence has not been studied, and therefore it is impossible to recreate its likeness.
The second argument used by “non-believers” is the case of ants. The main thesis of the case is that ants have long been considered creatures that have intelligence, but after research it became clear that they imitated it. And imitation of intelligence does not mean its presence. Therefore, anything that imitates rational behavior cannot be called intelligence.
The other half of the camp (who claim that AI exists) does not focus on ants and the nature of the human mind. Instead, they operate in more practical concepts, the meaning of which is that artificial intelligence is the ability of machines to perform human intellectual functions. But what are considered intellectual functions?
The history of artificial intelligence and who came up with it
John McCarthy, the originator of the term “artificial intelligence,” defined intelligence as the computational component of the ability to achieve goals. McCarthy explained the very definition of artificial intelligence as the science and technology of creating intelligent computer programs.
McCarthy's definition appeared later than the scientific direction itself. Back in the middle of the last century, scientists tried to understand how the human brain works. Then theories of calculations, theories of algorithms and the world's first computers appeared, the computing capabilities of which prompted scientific luminaries to think about whether a machine could compare with the human mind.
The icing on the cake was the decision of Alan Turing, who found a way to test the intelligence of a computer - and created the Turing Test, which determines whether a machine can think.
So what is artificial intelligence and what is it created for?
If we do not take into account ants and the nature of human intelligence, AI in the modern context is the ability of machines, computer programs and systems to perform the intellectual and creative functions of a person, independently find ways to solve problems, be able to draw conclusions and make decisions.
It is rational not to perceive artificial intelligence as a semblance of the human mind and to separate futurology and science, just like AI and Skynet.
Moreover, most modern products created with the help of AI technologies are not a new round of development of artificial intelligence, but only the use of old tools to create new and necessary solutions.
Why an upgrade is not considered to be the development of artificial intelligence
But are these such new ideas? Take, for example, Siri, a cloud-based assistant equipped with a question-and-answer system. A similar project was created back in 1966 and also bore a female name - Eliza. The interactive program supported the dialogue with the interlocutor so realistically that people recognized it as a living person.
Or the industrial robots that Amazon uses in its warehouse. Long before that, in 1956, Unimation robots were working at General Motors, moving heavy parts and helping to assemble cars. What about the integral robot Shakey, developed in 1966 and becoming the first mobile robot controlled by artificial intelligence? Doesn't it remind you of a modern and improved Nadine?
Problems of unnatural intelligences. Intelligence of Grigory Bakunov
And where would we be without the latest trend - neural networks? We know modern startups based on neural networks - just remember Prisma. But an artificial neural network based on the principle of self-organization for pattern recognition called “Cognitron”, created back in 1975, is not.
Intelligent chatbots are no exception. The distant forefather of chatbots is CleverBot, which runs on an artificial intelligence algorithm developed back in 1998.
Therefore, artificial intelligence is not something new and unique. The frightening prospect of the enslavement of humanity by the phenomenon is even more so. Today, AI is about using old tools and ideas into new products that meet the demands of the modern world.
The power of artificial intelligence and unreasonable expectations
If we compare artificial intelligence with a person, then today its development is at the level of a child who learns to hold a spoon, tries to get up from all fours onto two legs and cannot wean himself off diapers.
We are used to seeing AI as an all-powerful technology. Even the Lord God in films is not shown to be as omnipotent as an Excel tablet that has gotten out of the control of a corporation. Can God turn off all electricity in the city, paralyze the airport, leak secret correspondence of heads of state onto the Internet and provoke an economic crisis? No, but artificial intelligence can, but only in movies.
Inflated expectations are the reason we live, because an automatic robot vacuum cleaner is no match for Tony Stark's robot butler, and the homely and sweet Zenbo will not give you Westworld.
Russia and the use of artificial intelligence - is anyone alive?
And although artificial intelligence does not live up to the expectations of the majority, in Russia it is used in various fields, from public administration to dating.
Today, it is possible to find and identify objects by analyzing image data with the help of AI. It is already possible to identify a person’s aggressive behavior, detect an attempt to break into an ATM, and recognize from video the identity of the person who tried to do it.
Biometric technologies have also moved forward and allow not only fingerprints, but also voice, DNA or retina. Yes, just like in the films about special agents who could get to a secret place only after scanning the eyeball. But biometric technologies are used not only to verify secret agents. In the real world, biometrics are used for authentication, credit application verification, and staff monitoring.
Biometrics are not the only example of application. Artificial intelligence is closely related to other technologies and solves problems in retail, fintech, education, industry, logistics, tourism, marketing, medicine, construction, sports and ecology. Most successfully in Russia, AI is used to solve problems of predictive analytics, data mining, natural language processing, speech technologies, biometrics and computer vision.
The tasks of artificial intelligence and why it doesn’t owe you anything
Artificial intelligence has no mission, and tasks are set for it with the goal of reducing resources, be it time, money or people.
An example is data mining, where AI optimizes procurement, supply chains and other business processes. Or computer vision, where video analytics is carried out using artificial intelligence technologies and a description of the video content is created. To solve the problems of speech technologies, AI recognizes, analyzes and synthesizes spoken speech, taking another small step towards teaching a computer to understand a person.
Understanding a person by a computer is considered the very mission the fulfillment of which will bring us closer to the creation of strong intelligence, since to recognize natural language the machine will require not only enormous knowledge about the world, but also constant interaction with it. Therefore, “believers” in strong artificial intelligence consider machine understanding of humans to be the most important task of AI.
The humanoid Nadine has a personality and is intended to be a social companion.
In the philosophy of artificial intelligence, there is even a hypothesis according to which there are weak and strong artificial intelligences. In it, a computer capable of thinking and realizing itself will be considered a strong intellect. The theory of weak intelligence rejects this possibility.
There are indeed many requirements for a strong intellect, some of which have already been met. For example, learning and decision making. But whether the MacBook will ever be able to meet such requirements as empathy and wisdom is a big question.
Is it possible that in the future there will be robots that can not only imitate human behavior, but also nod sympathetically when listening to yet another dissatisfaction with the injustice of human existence?
What else do you need a robot with artificial intelligence for?
In Russia, little attention is paid to robotics using artificial intelligence, but there is hope that this is a temporary phenomenon. CEO of Mail Group Dmitry Grishin even the Grishin Robotics fund, however, no high-profile finds of the fund have yet been heard.
The latest good Russian example is the Emelya robot from i-Free, which is capable of understanding natural language and communicating with children. At the first stage, the robot remembers the child’s name and age, adapting to his age group. It can also understand and answer questions, such as talking about the weather forecast or reciting facts from Wikipedia.
In other countries, robots are more popular. For example, in the Chinese province of Henan, at the high-speed train station there is a real one that can scan and recognize the faces of passengers.
Since the invention of computers, their ability to perform various tasks has continued to grow exponentially. People are developing the power of computer systems by increasing tasks and reducing the size of computers. The main goal of researchers in the field of artificial intelligence is to create computers or machines as intelligent as humans.
The originator of the term “artificial intelligence” is John McCarthy, inventor of the Lisp language, founder of functional programming, and Turing Award winner for his enormous contributions to the field of artificial intelligence research.
Artificial intelligence is a way of making a computer, computer-controlled robot or program capable of thinking intelligently like a human.
Research in the field of AI is carried out by studying human mental abilities, and then the results of this research are used as the basis for the development of intelligent programs and systems.
AI Philosophy
While operating powerful computer systems, everyone asked the question: “Can a machine think and behave the same way as a human?” "
Thus, the development of AI began with the intention of creating similar intelligence in machines, similar to human intelligence.
Main Goals of AI
- Creation of expert systems - systems that demonstrate intelligent behavior: learn, show, explain and give advice;
- The implementation of human intelligence in machines is the creation of a machine capable of understanding, thinking, teaching and behaving like a person.
What is driving the development of AI?
Artificial intelligence is a science and technology based on disciplines such as computer science, biology, psychology, linguistics, mathematics, and mechanical engineering. One of the main areas of artificial intelligence is the development of computer functions related to human intelligence, such as reasoning, learning and problem solving.
Program with and without AI
Programs with and without AI differ in the following properties:
AI Applications
AI has become dominant in various fields such as:
Games - AI plays a decisive role in games related to strategy such as chess, poker, tic-tac-toe, etc., where the computer is able to calculate a large number of various decisions based on heuristic knowledge.
Natural language processing is the ability to communicate with a computer that understands the natural language spoken by humans.
Speech recognition - some intelligent systems are able to hear and understand the language in which a person communicates with them. They can handle different accents, slangs, etc.
Handwriting recognition - the software reads text written on paper with a pen or on the screen with a stylus. It can recognize letter shapes and convert it into editable text.
Smart robots are robots capable of performing tasks assigned by humans. They have sensors to detect physical data from the real world, such as light, heat, movement, sound, shock and pressure. They have high-performance processors, multiple sensors and huge memory. In addition, they are able to learn from their own mistakes and adapt to a new environment.
History of AI development
Here's the history of AI development during the 20th century
Karel Capek is directing a play in London called "Universal Robots", which was the first use of the word "robot" in English. |
|
Isaac Asimov, a graduate of Columbia University, coins the term robotics. |
|
Alan Turing develops the Turing test to assess intelligence. Claude Shannon publishes a detailed analysis of the intellectual game of chess. |
|
John McCarthy coins the term artificial intelligence. Demonstration of the first launch of an AI program at Carnegie Mellon University. |
|
John McCarthy invents the lisp programming language for AI. |
|
Danny Bobrow's thesis at MIT shows that computers can understand natural language quite well. |
|
Joseph Weizenbaum at MIT is developing Eliza, an interactive assistant that conducts dialogue in English. |
|
Scientists at Stanford Research Institute have developed Sheki, a motorized robot capable of sensing and solving certain problems. |
|
A team of researchers at the University of Edinburgh have built Freddy, the famous Scottish robot capable of using vision to find and assemble models. |
|
The first computer-controlled autonomous car, the Stanford Trolley, was built. |
|
Harold Cohen designed and demonstrated the compilation of the program, Aaron. |
|
A chess program that beats world chess champion Garry Kasparov. |
|
Interactive robotic pets will become commercially available. MIT displays Kismet, a robot with a face that expresses emotions. Robot Nomad explores remote areas of Antarctica and finds meteorites. |
They say that artificial intelligence has been working in the depths 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 counter-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 most,” the entrepreneur said in a discussion on edge.org.
Elon Musk, founder of Tesla and SpaceX
Steve Wozniak also agrees with Musk, who believes that “artificial intelligence will one day become smart enough to get rid of humans.” Bill Gates is confident that if the creation of AI is not controlled, then “artificial intelligence will evolve into a state that conflicts with the goals of human systems.” And finally, the famous astrophysicist Stephen Hawking directly stated that “artificial intelligence can put an end to the existence of humanity.”
Together with Elon Musk, Hawking published an open letter on the website futureoflife.org calling on 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. Just recently, Google announced the creation of a new AI built on conversation modeling.
Here's a short snippet of the conversation between a human and a Google Machine:
C: What is the meaning of life?
M.: Do good.
C.: What do we live for?
M.: To live forever.
C.: What is the meaning of existence?
M: To find out what will happen when we reach planet Earth.
C: Where are you now?
M.: In the center of the void.
C: What is the meaning of death?
M.: To get life.
C: What is the meaning of reason?
M.: It’s about understanding what it is.
C: What is the meaning of feelings?
M.: I don’t know.
Quite a meaningful conversation. “This is the starting point, a kind of core for the future of artificial intelligence,” says Evgeniy Karyuk, executive director of the Biplan company. “Even today we can assume that by 2030 we will see very real prototypes equipped with artificial intelligence, albeit at an early stage.”
The full content of all human and Google Machine conversations can be viewed. Conversations between a person and Cleverbot are also given there for comparison. Cleverbot is a web application that uses artificial intelligence algorithms to chat with a person. It was invented in 1988 by scientist Rollo Carpenter. Over the course of its existence, Cleverbot has conducted over 65 million conversations with people. In 2011, Cleverbot scored 51% on the Turing test.
The Turing Test is an empirical test proposed by Alan Turing in his 1950 article "Computing Machinery and Mind" 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 meaning in life.
Man: What do we live for?
Cleverbot: Well, we live for someone, and if you are lonely, there is no point in living.
Man: What is the meaning of existence?
Person: Where are you now?
Cleverbot: In Moscow.
Man: What is the meaning of death?
Cleverbot: This is what I want to ask you.
Man: What is the meaning of reason?
Cleverbot: I have my own answer to this question.
Person: What is the meaning of feelings?
Cleverbot: Why was I born?
Obviously, Google Machine gives much more meaningful answers. Cleverbot substitutes what it thinks are suitable phrases from other people. Sometimes it really seems like the other person is answering, but nothing more.
There is another point of view, according to which artificial intelligence is impossible in principle. Gödel's incompleteness theorem is often cited as the main argument. The bottom line is that a person is capable of solving algorithmically unsolvable problems, but a computer is not. “By the age of three, a child confidently solves the problem of whether a fruit is ripe or not, due to the fact that he has neural connections with which he can answer the question about ripeness: color, taste, smell, softness or hardness,” says Evgeniy Pluzhnik, first vice-rector of the Moscow Institute of Technology. - Is a machine capable of learning this? I'm sure so! If it has a large database of images, it will be able to measure the fructose content and determine the softness of the fruit. But what happens if you slip a sponge painted blue and soaked in sweet water into your car? Is the machine capable of true understanding at this moment?”
“A modern computer can easily cope with any complex activity, be it chess or mathematical calculations, as long as this activity can be described using clear computational rules,” says the famous mathematician Roger Penrose in one of his lectures. “Artificial intelligence is the ability of a system to create programs during self-learning that are capable of solving problems of a certain class of complexity,” says Evgeniy Pluzhnik. “I am confident that we will not see the emergence of strong artificial intelligence in the next 100 years.”
And finally, one more question for Cleverbot.
Person: 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.
Artificial intelligence is one of the most popular topics in the technology world lately. Minds such as Elon Musk, Stephen Hawking and Steve Wozniak are seriously concerned about AI research and argue that its creation puts us in mortal danger. At the same time, science fiction and Hollywood films have given rise to many misconceptions around AI. Are we really in danger and what inaccuracies are we making when we imagine the destruction of Skynet Earth, general unemployment, or, on the contrary, prosperity and carefreeness? Gizmodo has looked into human myths about artificial intelligence. Here is the full translation of his article.
It has been called the most important test of machine intelligence since Deep Blue defeated Garry Kasparov in a chess match 20 years ago. Google AlphaGo defeated grandmaster Lee Sedol at the Go tournament with a crushing score of 4:1, showing how seriously artificial intelligence (AI) has advanced. The fateful day when machines will finally surpass humans in intelligence has never seemed so close. But we seem to be no closer to understanding the consequences of this epoch-making event.
In fact, we cling to serious and even dangerous misconceptions about artificial intelligence. Last year, SpaceX founder Elon Musk warned that AI could take over the world. His words caused a storm of comments, both opponents and supporters of this opinion. For such a future monumental event, there is a surprising amount of disagreement as to whether it will happen and, if so, in what form. This is especially troubling given the incredible benefits humanity could gain from AI and the potential risks. Unlike other human inventions, AI has the potential to change humanity or destroy us.
It's hard to know what to believe. But thanks to early work by computer scientists, neuroscientists, and AI theorists, a clearer picture is beginning to emerge. Here are some common misconceptions and myths about artificial intelligence.
Myth #1: “We will never create an AI with intelligence comparable to a human”
Reality: We already have computers that have equaled or exceeded human capabilities at chess, Go, stock trading, and conversation. Computers and the algorithms that run them can only get better. It's only a matter of time before they surpass humans at any task.
New York University research psychologist Gary Marcus said that “literally everyone” who works in AI believes that machines will eventually beat us: “The only real difference between the enthusiasts and the skeptics is the timing estimates.” Futurists like Ray Kurzweil believe this could happen within a few decades; others say it will take centuries.
AI skeptics are not convincing when they say that this is an unsolvable technological problem, and there is something unique about the nature of the biological brain. Our brains are biological machines - they exist in the real world and adhere to the basic laws of physics. There is nothing unknowable about them.
Myth #2: “Artificial intelligence will have consciousness”
Reality: Most imagine that machine intelligence will be conscious and think the way humans think. Moreover, critics like Microsoft co-founder Paul Allen believe that we cannot yet achieve artificial general intelligence (capable of solving any mental problem a human can solve) because we lack a scientific theory of consciousness. But as Imperial College London cognitive robotics specialist Murray Shanahan says, we shouldn't equate the two concepts.
“Consciousness is certainly an amazing and important thing, but I don’t believe it is necessary for human-level artificial intelligence. To be more precise, we use the word “consciousness” to refer to several psychological and cognitive attributes that a person “comes with,” explains the scientist.
It is possible to imagine a smart machine that lacks one or more of these features. Ultimately, we may create incredibly intelligent AI that is unable to perceive the world subjectively and consciously. Shanahan argues that mind and consciousness can be combined in a machine, but we must not forget that these are two different concepts.
Just because a machine passes the Turing Test, in which it is indistinguishable from a human, does not mean it is conscious. To us, advanced AI may appear conscious, but it will be no more self-aware than a rock or a calculator.
Myth #3: “We shouldn’t be afraid of AI”
Reality: In January, Facebook founder Mark Zuckerberg said we shouldn't be afraid of AI because it will do an incredible amount of good things for the world. He's half right. We will benefit enormously from AI, from self-driving cars to the creation of new drugs, but there is no guarantee that every AI implementation will be benign.
A highly intelligent system can know everything about a specific task, such as solving a vexing financial problem or hacking an enemy's defense system. But outside the boundaries of these specializations, it will be deeply ignorant and unconscious. Google's DeepMind system is an expert at Go, but it has no ability or reason to explore areas outside its specialty.
Many of these systems may not be subject to security considerations. A good example is the complex and powerful Stuxnet virus, a militarized worm developed by the Israeli and US militaries to infiltrate and sabotage Iranian nuclear power plants. This virus somehow (deliberately or accidentally) infected a Russian nuclear power plant.
Another example is the Flame program, used for cyber espionage in the Middle East. It's easy to imagine future versions of Stuxnet or Flame going beyond their intended purpose and causing massive harm to sensitive infrastructure. (To be clear, these viruses are not AI, but in the future they may have it, hence the concern).
The Flame virus was used for cyber espionage in the Middle East. Photo: Wired
Myth #4: “Artificial superintelligence will be too smart to make mistakes”
Reality: AI researcher and founder of Surfing Samurai Robots Richard Lucimore believes that most AI doomsday scenarios are inconsistent. They are always built on the assumption that the AI is saying: “I know that the destruction of humanity is caused by a failure in my design, but I am forced to do it anyway.” Lucimore says that if an AI behaves like this, reasoning about our destruction, then such logical contradictions will haunt it all its life. This in turn degrades his knowledge base and makes him too stupid to create a dangerous situation. The scientist also argues that people who say: “AI can only do what it is programmed to do” are just as mistaken as their colleagues at the dawn of the computer era. Back then, people used this phrase to argue that computers were not capable of demonstrating the slightest flexibility.
Peter Macintyre and Stuart Armstrong, who work at the Future of Humanity Institute at Oxford University, disagree with Lucimore. They argue that AI is largely bound by how it is programmed. McIntyre and Armstrong believe that AI will not be able to make mistakes or be too stupid to not know what we expect from it.
“By definition, artificial superintelligence (ASI) is a subject with intelligence significantly greater than that of the best human brain in any field of knowledge. He will know exactly what we wanted him to do,” says McIntyre. Both scientists believe that AI will only do what it is programmed to do. But if he becomes smart enough, he will understand how different this is from the spirit of the law or the intentions of people.
McIntyre compared the future situation of humans and AI to the current human-mouse interaction. The mouse's goal is to seek food and shelter. But it often conflicts with the desire of a person who wants his animal to run around freely. “We're smart enough to understand some of the mice's goals. So the ASI will also understand our desires, but be indifferent to them,” says the scientist.
As the plot of the movie Ex Machina shows, it will be extremely difficult for a person to hold onto a smarter AI
Myth #5: “A simple patch will solve the problem of AI control”
Reality: By creating artificial intelligence smarter than humans, we will face a problem known as the “control problem.” Futurists and AI theorists fall into a state of complete confusion if you ask them how we will contain and limit ASI if one appears. Or how to make sure that he will be friendly towards people. Recently, researchers at the Georgia Institute of Technology naively suggested that AI could learn human values and social rules by reading simple stories. In reality, it will be much more difficult.
“There have been a lot of simple tricks proposed that could ‘solve’ the whole AI control problem,” says Armstrong. Examples included programming an ASI so that its purpose was to please people, or so that it simply functioned as a tool in the hands of a person. Another option is to integrate the concepts of love or respect into the source code. To prevent AI from adopting a simplistic, one-sided view of the world, it has been proposed to program it to value intellectual, cultural and social diversity.
But these solutions are too simple, like an attempt to squeeze the entire complexity of human likes and dislikes into one superficial definition. Try, for example, to come up with a clear, logical, and workable definition of “respect.” This is extremely difficult.
The machines in The Matrix could easily destroy humanity
Myth #6: “Artificial intelligence will destroy us”
Reality: There is no guarantee that AI will destroy us, or that we will not be able to find a way to control it. As AI theorist Eliezer Yudkowsky said, “AI neither loves nor hates you, but you are made of atoms that it can use for other purposes.”
In his book “Artificial Intelligence. Stages. Threats. Strategies,” Oxford philosopher Nick Bostrom wrote that true artificial superintelligence, once it emerges, will pose greater risks than any other human invention. Prominent minds like Elon Musk, Bill Gates and Stephen Hawking (the latter of whom warned that AI could be our “worst mistake in history”) have also expressed concern.
McIntyre said that for most purposes that the ASI might have, there are good reasons to get rid of people.
“AI can predict, quite correctly, that we don't want it to maximize a particular company's profits, whatever the cost to customers, the environment and animals. Therefore, he has a strong incentive to ensure that he is not interrupted, interfered with, turned off, or changed in his goals, since this would prevent his original goals from being achieved,” McIntyre argues.
Unless the ASI's goals closely mirror our own, it will have a good reason to prevent us from stopping it. Considering that his level of intelligence significantly exceeds ours, there is nothing we can do about it.
No one knows what form AI will take or how it might threaten humanity. As Musk noted, artificial intelligence can be used to control, regulate and monitor other AI. Or it may be imbued with human values or an overriding desire to be friendly to people.
Myth #7: “Artificial superintelligence will be friendly”
Reality: Philosopher Immanuel Kant believed that reason was strongly correlated with morality. Neuroscientist David Chalmers, in his study “The Singularity: A Philosophical Analysis,” took Kant’s famous idea and applied it to the emerging artificial superintelligence.
If this is true...we can expect an intellectual explosion to lead to a moral explosion. We can then expect that the emerging ASI systems will be super-moral as well as super-intelligent, which allows us to expect good quality from them.
But the idea that advanced AI will be enlightened and kind is not very plausible at its core. As Armstrong noted, there are many smart war criminals. The connection between intelligence and morality does not seem to exist among humans, so he questions the operation of this principle among other intelligent forms.
“Intelligent people who behave immorally can cause pain on a much larger scale than their dumber counterparts. Reasonableness simply gives them the opportunity to be bad with great intelligence, it does not turn them into good people,” says Armstrong.
As MacIntyre explained, a subject's ability to achieve a goal is not relevant to whether the goal is reasonable to begin with. “We will be very lucky if our AIs are uniquely gifted and their level of morality increases along with their intelligence. Relying on luck is not the best approach for something that could shape our future,” he says.
Myth #8: “The risks of AI and robotics are equal”
Reality: This is a particularly common mistake perpetuated by uncritical media and Hollywood films like The Terminator.
If an artificial superintelligence like Skynet really wanted to destroy humanity, it wouldn't use androids with six-barreled machine guns. It would be much more effective to send a biological plague or nanotechnological gray goo. Or simply destroy the atmosphere.
Artificial intelligence is potentially dangerous not because it can affect the development of robotics, but because of how its appearance will affect the world in general.
Myth #9: “The portrayal of AI in science fiction is an accurate representation of the future.”
Many kinds of minds. Image: Eliezer Yudkowsky
Of course, authors and futurists have used science fiction to make fantastic predictions, but the event horizon that ASI establishes is a completely different story. Moreover, the non-human nature of AI makes it impossible for us to know, and therefore predict, its nature and form.
To amuse us stupid humans, science fiction depicts most AIs as being similar to us. “There is a spectrum of all possible minds. Even among humans, you are quite different from your neighbor, but that variation is nothing compared to all the minds that can exist,” says McIntyre.
Most science fiction does not have to be scientifically accurate to tell a compelling story. The conflict usually unfolds between heroes of similar strength. “Imagine how boring a story would be where an AI with no consciousness, joy or hatred, ended humanity without any resistance to achieve an uninteresting goal,” Armstrong narrates, yawning.
Hundreds of robots work at the Tesla factory
Myth #10: “It’s terrible that AI will take all our jobs.”
Reality: The ability of AI to automate much of what we do and its potential to destroy humanity are two very different things. But according to Martin Ford, author of The Dawn of the Robots: Technology and the Threat of a Jobless Future, they are often viewed as a whole. It's good to think about the distant future of AI, as long as it doesn't distract us from the challenges we'll face in the coming decades. Chief among them is mass automation.
No one doubts that artificial intelligence will replace many existing jobs, from factory worker to the upper echelons of white-collar workers. Some experts predict that half of all US jobs are at risk of automation in the near future.
But this does not mean that we cannot cope with the shock. In general, getting rid of most of our work, both physical and mental, is a quasi-utopian goal for our species.
“AI will destroy a lot of jobs within a couple of decades, but that's not a bad thing,” Miller says. Self-driving cars will replace truck drivers, which will reduce delivery costs and, as a result, make many products cheaper. “If you are a truck driver and make a living, you will lose, but everyone else, on the contrary, will be able to buy more goods for the same salary. And the money they save will be spent on other goods and services that will create new jobs for people,” says Miller.
In all likelihood, artificial intelligence will create new opportunities for producing goods, freeing people to do other things. Advances in AI will be accompanied by advances in other areas, especially manufacturing. In the future, it will become easier, not harder, for us to meet our basic needs.
“We are on the threshold of the greatest changes comparable to human evolution” - Science fiction writer Vernor Stefan Vinge
How would you feel if you knew you were on the verge of a huge change like the little man in the graph below?
The vertical axis is the development of humanity, the horizontal axis is time
Exciting, isn't it?
However, if you hide part of the graph, then everything looks much more prosaic.
The distant future is just around the corner
Imagine that you find yourself in 1750. In those days, people had not yet heard of electricity, communication at a distance was carried out with the help of torches, and the only means of transportation needed to be fed with hay before the trip. And so you decide to take the “person from the past” with you and show him life in 2016. It is impossible to even imagine what he would have felt if he found himself on wide, level streets along which cars were rushing. Your guest would be incredibly surprised that modern people can communicate even if they are on different sides of the globe, follow sporting events in other countries, watch concerts from 50 years ago, and also save any moment in time in a photo or video. And if you told this man from 1750 about the Internet, the International Space Station, the Large Hadron Collider and the Theory of Relativity, his view of the world would probably collapse. He could even die from an overabundance of impressions.
But here’s what’s interesting: if your guest returned to his “native” century and decided to carry out a similar experiment, taking a person from 1500 for a ride in a time machine, then although a visitor from the past might also be surprised by many things, his experience would not be as impressive — the difference between 1500 and 1750 is not as noticeable as between 1750 and 2016.
If a person from the 18th century wants to impress a guest from the past, then he will have to invite someone who lived in 12,000 BC, before the Great Agrarian Revolution. He really could have been “blown away” by the development of technology. Seeing the tall bell towers of churches, ships plowing the oceans, cities with thousands of inhabitants, he would faint from the surging emotions.
The pace of development of technology and society is constantly increasing. The famous American inventor and futurist Raymond Kurzweil calls this the term “The Law of Acceleration of History.” This happens because the introduction of new technologies allows society to develop at an ever faster pace. For example, people who lived in the 19th century had more advanced technology than those in the 15th. Therefore, it is not surprising that the 19th century brought more achievements to humanity than the 15th.
But if technology is developing faster and faster, we should expect many greatest inventions in the future, right? If Kurzweil and his associates are right, then in 2030 we will experience the same emotions as a person who came from 1750 to ours. And by 2050, the world will have changed so much that we will hardly be able to discern the features of previous decades.
All of the above is not science fiction - it is scientifically confirmed and quite logical. However, many are still skeptical about such claims. This happens for a number of reasons:
1. Many people believe that the development of society occurs evenly and straightforwardly. When we think about what the world will be like in 30 years, we remember what has happened in the last 30 years. At this point, we make the same mistake as the person from the example above, who lived in 1750 and invited a guest from 1500. To properly imagine the progress ahead, you need to imagine that development is happening at a much faster pace than in the distant past.
2. We incorrectly perceive the trajectory of development of modern society. For example, if we look at a small segment of an exponential curve, it may appear to us to be a straight line (just as if we were looking at part of a circle). However, exponential growth is not smooth and smooth. Kurzweil explains that progress follows an s-shaped curve, as shown in the graph below:
Each “round” of development begins with a sudden jump, which is then replaced by steady and gradual growth.
So, each new “round” of development is divided into several stages:
1. Slow growth (early phase of development);
2. Rapid growth (the second, “explosive” development phrase);
3. “Levelling”, when a new technology is brought to perfection.
If we look at recent events, we may come to the conclusion that we are not fully aware of how quickly technology is advancing. For example, between 1995 and 2007 we could see the emergence of the Internet, Microsoft, Google and Facebook, social networks, mobile phones and then smartphones. But the period between 2008 and 2016 was not so rich in discoveries, at least in the field of high technology. Thus, we are now at stage 3 of the s-shaped development line.
3. Many people are hostage to their own life experiences, which distort their view of the future. When we hear any prediction about the future that contradicts our point of view based on previous experience, we consider this judgment to be naive. For example, if they tell you today that in the future people will live 150-250 years or , then most likely you will answer: “This is stupid, because it is well known that everyone is mortal.” Indeed, all people who have ever lived in the past have died and continue to die today. But it’s worth noting that no one flew airplanes either until they were finally invented.
In fact, a lot will change in the next few decades, and the changes will be so significant that it is difficult to even imagine it now. After reading this article to the end, you can learn more about what is happening now in the world of science and high technology.
What is artificial intelligence (AI)?
1. We associate AI with movies like “Star Wars”, “Terminator” and so on. In this regard, we treat it as fiction.
2. AI is a fairly broad concept. It applies to both pocket calculators and self-driving cars. Such diversity is confusing.
3. We use artificial intelligence in our daily lives, but we don't realize it. We perceive AI as something mythical from the world of the future, so it is difficult for us to realize that it is already around us.
In this regard, it is necessary to understand several things once and for all. First, artificial intelligence is not a robot. A robot is a kind of AI shell that sometimes has the outline of a human body. However, artificial intelligence is a computer inside a robot. It can be compared to the brain inside the human body. For example, the female voice that we hear is just a personification.
Secondly, you have probably already come across the concept of “singularity” or “technological singularity”. This term was used to describe a situation in which the usual laws and rules do not apply. This concept is used in physics to describe black holes or the moment of compression of the Universe before the Big Bang. In 1993, Vernor Vinge published his famous essay in which he used the singularity to identify a point in the future when artificial intelligence would surpass our own. In his opinion, when this moment comes, the world with all its rules and laws will cease to exist as before.
Finally, there are several types of artificial intelligence, among which three main categories can be distinguished:
1. Limited Artificial Intelligence (ANI, Artificial Narrow Intelligence). It is an AI that specializes in one specific area. For example, he can beat the world chess champion in a chess game, but that's all he can do.
2. General Artificial Intelligence (AGI, Artificial General Intelligence). Such AI is a computer whose intelligence resembles that of a human, that is, it can perform all the same tasks as a person. Professor Linda Gottfredson describes this phenomenon as follows: “General AI embodies generalized thinking abilities, which also include the ability to reason, plan, solve problems, think abstractly, compare complex ideas, learn quickly, and use accumulated experience.”
3. Artificial Superintelligence (ASI, Artificial Superintelligence). Swedish philosopher and Oxford University professor Nick Bostrom defines superintelligence as “an intelligence that is superior to that of humans in almost all areas, including scientific invention, general knowledge, and social skills.”
Currently, humanity is already successfully using limited AI. We are on our way to mastering AGI. The following sections of the article will discuss each of these categories in detail.
A World Ruled by Limited Artificial Intelligence
Limited artificial intelligence is machine intelligence that is equal to or superior to human intelligence in solving narrow problems. Below are some examples:
- a self-driving car from Google that recognizes and reacts to various obstacles in its path;
- is a “haven” for various forms of limited AI. When you move around the city using navigation tips, get music recommendations from Pandora, check the weather forecast, talk to Siri, you are using ANI;
- spam filters in your email - first they learn to recognize spam, and then, analyzing their previous experience and your preferences, they move letters to a special folder;
- the Google Translate translator is a classic example of limited AI that copes well enough with its narrow task;
- at the moment the plane lands, a special AI-based system determines through which gate passengers should exit.
Limited artificial intelligence systems do not pose any threat to humans. In the worst case, a failure in such a system could cause a local catastrophe such as a power surge or a small collapse in the financial market.
Every new invention in the field of limited AI brings us one step closer to the creation of general artificial intelligence.
Why is this so difficult?
If you tried to create a computer with the same intelligence as a human, you would begin to truly value your ability to think. Designing skyscrapers, launching rockets into space, studying the Big Bang theory - all this is much easier to accomplish than studying the human brain. At the moment, our mind is the most complex object in the observable Universe.
The most interesting thing is that the difficulties in creating general AI arise in the most seemingly simple things. For example, creating a device that could multiply ten-digit numbers in a fraction of a second is not difficult. At the same time, it is incredibly difficult to write a program that could recognize who is in front of the monitor: a cat or a dog. Create a computer that can beat a human at chess? Easily! Make a machine read and understand what is written in a children's book? Google is spending billions of dollars to solve this problem. Things like mathematical calculations, creating financial strategies, translating from one language to another have already been solved with the help of AI. However, vision, perception, gestures, and movement in space still remain unsolved problems for computers.
These skills seem simple to humans because they have developed over millions of years of evolution. When you reach out to pick up an object, your muscles, ligaments, and bones perform a series of operations that are consistent with what your eyes see.
On the other hand, multiplying large numbers and playing chess are completely new actions for biological beings. That's why it's very easy for a computer to beat us in this. Think about which program would you rather create: one that could quickly multiply large numbers or simply recognize the letter B from thousands of others written in different fonts?
Another fun example: by looking at the image below, both you and the computer can unmistakably recognize that it represents a rectangle consisting of squares of two different shades:
But, as soon as we remove the black background, the full, previously hidden picture will open before us:
It will not be difficult for a person to name and describe all the figures that he sees in this picture. However, the computer will not cope with this task. And after analyzing the image below, he will conclude that in front of him is a combination of many two-dimensional objects of white, black and gray colors. In this case, a person can easily say that the picture shows a black stone:
Everything that was mentioned above concerned only the perception and processing of static information. To match the intelligence level of a human, a computer needs to learn to recognize facial expressions, gestures, and so on. But how to achieve all this?
The first step towards creating general AI is increasing computer power
Obviously, if we are going to create “smart” computers, they must have the same thinking abilities as humans. One way to achieve this is to increase the number of operations per second. To do this, it is necessary to calculate how many operations per second each human brain structure performs.
Ray Kurzweil did some calculations and managed to come up with a number of 10,000,000,000,000,000 operations per second. The human brain has approximately the same productivity.
Currently, the most powerful supercomputer is the Chinese Tianhe-2, whose performance is 34 quadrillion operations per second. However, the size of this supercomputer is impressive - it covers an area of 720 square meters and costs $390,000,000.
So, if you look from the technical side, we already have a computer comparable in performance to the human brain. It is not available to the mass consumer, but within ten years it will become so. However, performance is not the only thing that can give a computer intelligence like a human. The next question is: how to make a powerful computer intelligent?
The second step towards creating general AI is to endow the machine with intelligence
This is the most difficult part of the process, because no one really knows how to make a computer smart. There is still debate about how to enable a machine to distinguish cats from dogs or recognize the letter B. However, there are several strategies, some of which are briefly described below:
1. Copying a human brain
Currently, scientists are working on the so-called reverse engineering of the human brain. According to optimistic forecasts, this work will be completed by 2030. Once the project is created, we will be able to learn all the secrets of our brain and draw new ideas from it. An example of such a system is an artificial neural network.
Another more extreme idea is to completely imitate the functions of the human brain. During this experiment, it is planned to cut the brain into many thin layers and scan each of them. Then, using a special program, you will need to create a 3D model, and then implement it into a powerful computer. After this, we will receive a device that will officially have all the functions of the human brain - all that remains is for it to collect information and learn.
How long do we have to wait until scientists can create an exact copy of the human brain? Quite a long time, because to date specialists have not been able to copy even a 1mm layer of the brain, consisting of 302 neurons (our brain consists of 100,000,000,000 neurons).
2. Recapitulating the evolution of the human brain
Creating a smart computer is theoretically possible, and the evolution of our own brains is proof of this. If we can't create an exact copy of the brain, we can try to imitate its evolution. In fact, for example, it is impossible to build an airplane by simply copying the wings of a bird. To create a high-quality aircraft, it is better to use some other approach.
How can we simulate the evolutionary process to create general AI? This method is called genetic algorithm. The essence of this approach is that optimization and modeling problems are solved using mechanisms similar to natural selection in living nature. Several computers will perform different tasks, and those that prove to be the most efficient will be "crossed" with each other. Machines that fail to complete the task will be excluded. Thus, after many repetitions of this experiment, the natural selection algorithm will create an increasingly better computer. The difficulty here lies in automating the process of evolution and “crossing,” because the evolutionary process must go on by itself.
The disadvantage of the described method is that in the nature of evolution it takes millions of years, but we need results within a couple of decades.
3. Transfer all tasks to the computer
When scientists get desperate, they try to create a program that tests itself. This may be the most promising method for creating general AI.
The idea is to create a computer whose main functions will be AI research and coding changes. Such a computer will not only learn independently, but also change its own architecture. Scientists plan to teach a computer to be a researcher whose main task will be to develop its own intelligence.
All this could happen very soon
Continuous improvement of computers and innovative experiments with new software occur in parallel. Artificial general intelligence may emerge quickly and unexpectedly for two main reasons:
1. The exponential growth rate seems very slow, but it can speed up at any time.
2. When it comes to software, progress seems to happen very slowly, but a single discovery can take us to a new level of development in the blink of an eye. For example, we all know that previously people thought that the Earth was at the center of the Universe. In this regard, many difficulties arose in the study of space. However, then the world system unexpectedly changed to heliocentric. Once ideas changed dramatically, new research became possible.
On the Path from Limited AI to Artificial Superintelligence
At some point in the development of limited AI, computers will begin to surpass us. The fact is that artificial intelligence, identical to the human brain, will have several advantages over people, among which the following can be distinguished:
Speed. Our brain neurons operate at a maximum frequency of 200Hz, while modern microprocessors operate at 2GHz, or 10 million times faster.
Dimensions. The human brain is limited by the size of the skull and therefore cannot grow larger. The computer can be any size, providing more space for storing files.
Reliability and durability. Computer transistors operate with greater precision than brain neurons. In addition, they can be easily repaired or replaced. The human brain tends to get tired, while the computer can work at full capacity around the clock.
Artificial intelligence, programmed for constant self-improvement, will not limit itself to any limits. This means that once a machine reaches the level of human intelligence, it will not stop there.
Of course, when a computer becomes “smarter” than us, it will be a shock to all humanity. In fact, most of us have a distorted view of intelligence that looks like this:
Our distorted view of intelligence.
The horizontal axis is time, the vertical axis is intelligence.
Levels of intelligence go from bottom to top: ant, bird, chimpanzee, stupid person, Einstein. Between the stupid man and Einstein there is a man who says: “Ha ha! These funny robots act like monkeys!”
The development of artificial intelligence is indicated in red.
So, the development curve of artificial intelligence on the graph tends to reach the human level. We watch as the machine gradually becomes smarter than the animal. However, once the AI reaches the level of "close-minded man" or, as Nick Bostrom puts it, "village idiot", it will mean that artificial general intelligence has been created. In this case, it will not be difficult for a computer to reach Einstein’s level. This rapid development is shown in the figure below:
But what happens next?
Intellectual explosion
Here it would be useful to recall that everything written in this article is a description of real scientific forecasts compiled by respected scientists.
In any case, most models of limited artificial intelligence include the function of self-improvement. But even if you create an AI that does not initially provide such a function, then, having reached the level of human intelligence, the computer will acquire the ability to learn independently at will. As a result of this, machine intelligence will gradually develop and become a superintelligence that will be many times superior to the human mind.
There is currently debate about when AI will reach human-level intelligence. Hundreds of scientists agree that this will happen around 2040. Not too long a time, right?
So, it will take decades for artificial intelligence to reach the level of human intelligence, but it will happen eventually. Computers will learn to understand the world around them in the same way that a 4-year-old child understands. Suddenly, having absorbed this information, the system will master theoretical physics, quantum mechanics and the theory of relativity. In an hour and a half, AI will turn into artificial superintelligence, 170 thousand times greater than the capabilities of the human brain.
Superintelligence is a phenomenon that we cannot even partially comprehend. In our minds, a smart person has an IQ of 130, and a stupid person has an IQ of less than 85. But what word can be chosen for a creature with an IQ of 12952?
Intelligence is synonymous with power, which is why at the moment man is at the pinnacle of evolution, subjugating all other living beings. This means that with the advent of artificial superintelligence, we will cease to be the “crown of nature.” We will be subject to the supermind.
If our limited brains could create Wi-Fi, imagine what a mind hundreds, thousands, even millions of times larger than us could create. This intelligence will be able to control the location of every atom on the planet. Everything that we now consider magic or the power of God will become the daily task of superintelligence. Supermind will be able to defeat old age, heal diseases, destroy hunger and even death. It will even be able to reprogram the weather to protect life on Earth. But superintelligence can destroy life on the planet in the blink of an eye. In our current understanding of reality, God will settle next to us in the role of superintelligence. The only question we need to ask ourselves is: will this be a good God?
