Endowing AI with noble goals may not preventunintended consequences.
Credit: Iyad Rahwan
New Findings From Theoretical Computer Science
We are fascinated by machines that can control cars, compose symphonies, or defeat people at chess, Go, or Jeopardy! While more progress is being made all the time in Artificial Intelligence (AI), some scientists and philosophers warn of the dangers of an uncontrollable superintelligent AI. Using theoretical calculations, an international team of researchers, including scientists from the Center for Humans and Machines at the Max Planck Institute for Human Development, shows that it would not be possible to control a superintelligent AI. The study was published in the Journal of Artificial Intelligence Research.
Suppose someone were to program an AI system with intelligence superior to that of humans, so it could learn independently. Connected to the Internet, the AI may have access to all the data of humanity. It could replace all existing programs and take control all machines online worldwide. Would this produce a utopia or a dystopia? Would the AI cure cancer, bring about world peace, and prevent a climate disaster? Or would it destroy humanity and take over the Earth?
Computer scientists and philosophers have asked themselves whether we would even be able to control a superintelligent AI at all, to ensure it would not pose a threat to humanity. An international team of computer scientists used theoretical calculations to show that it would be fundamentally impossible to control a super-intelligent AI.
“A super-intelligent machine that controls the world sounds like science fiction. But there are already machines that perform certain important tasks independently without programmers fully understanding how they learned it. The question therefore arises whether this could at some point become uncontrollable and dangerous for humanity”, says study co-author Manuel Cebrian, Leader of the Digital Mobilization Group at the Center for Humans and Machines, Max Planck Institute for Human Development.
Scientists have explored two different ideas for how a superintelligent AI could be controlled. On one hand, the capabilities of superintelligent AI could be specifically limited, for example, by walling it off from the Internet and all other technical devices so it could have no contact with the outside world – yet this would render the superintelligent AI significantly less powerful, less able to answer humanities quests. Lacking that option, the AI could be motivated from the outset to pursue only goals that are in the best interests of humanity, for example by programming ethical principles into it. However, the researchers also show that these and other contemporary and historical ideas for controlling super-intelligent AI have their limits.
In their study, the team conceived a theoretical containment algorithm that ensures a superintelligent AI cannot harm people under any circumstances, by simulating the behavior of the AI first and halting it if considered harmful. But careful analysis shows that in our current paradigm of computing, such algorithm cannot be built.
“If you break the problem down to basic rules from theoretical computer science, it turns out that an algorithm that would command an AI not to destroy the world could inadvertently halt its own operations. If this happened, you would not know whether the containment algorithm is still analyzing the threat, or whether it has stopped to contain the harmful AI. In effect, this makes the containment algorithm unusable”, says Iyad Rahwan, Director of the Center for Humans and Machines.
Based on these calculations the containment problem is incomputable, i.e. no single algorithm can find a solution for determining whether an AI would produce harm to the world. Furthermore, the researchers demonstrate that we may not even know when superintelligent machines have arrived, because deciding whether a machine exhibits intelligence superior to humans is in the same realm as the containment problem.
The study “Superintelligence cannot be contained: Lessons from Computability Theory“ was published in the Journal of Artificial Intelligence Research. Other researchers on the study include Andres Abeliuk from the University of Southern California, Manuel Alfonseca from the Autonomous University of Madrid, Antonio Fernandez Anta from the IMDEA Networks Institute and Lorenzo Coviello.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Superintelligent AI
- AI Already Skilled At Deceiving Humans - And That's A Problem, Experts Warn
Mysterious goals' Near-term, the paper's authors see risks for AI to commit fraud or tamper with elections. In their worst-case scenario, they warned, a superintelligent AI could pursue power and ...
- Artificial intelligence systems develop skill for deception, experts warn
Current AI systems, designed to be honest, have developed a troubling skill for deception. From tricking human players in online games of ‘world conquest’, to hiring humans to solve ...
- AI systems are already deceiving us -- and that's a problem, experts warn
Experts have long warned about the threat posed by artificial intelligence going rogue -- but a new research paper suggests it's already happening.Current AI systems, designed to be honest, have ...
- Superintelligent AI could lead to 15-hour work week by 2030 as 'Land of Plenty' era begins
Express US spoke to Nick Bostrom, one of the pioneers of simulation theory, about how humans could be living in 'The Land of Plenty' by 2030 - thanks to superintelligent AI.
- 'It would be within its natural right to harm us to protect itself': How humans could be mistreating AI right now without even knowing it
How can we truly know if AI is sentient? We do not yet fully understand the nature of human consciousness, so we cannot discount the possibility that today's AI is indeed sentient — and that we are ...
Go deeper with Google Headlines on:
Superintelligent AI
[google_news title=”” keyword=”superintelligent AI” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Super-intelligent machines
- Is This Beaten-Down Artificial Intelligence Stock a No-Brainer Buy Right Now?
Since its founding in 2015, the business has focused on utilizing AI and machine learning (ML) to better analyze risk and serve customers in the insurance industry with renters, homeowners, auto, pet, ...
- Artificial General Intelligence (AGI): Why Are People Spooked About It?
Artificial General Intelligence (AGI) is growing at a very fast pace, stirring concerns because of its super-intelligence ...
- Patrick Mahomes says Travis Kelce is 'super intelligent' despite party hard image: 'He puts on this persona'
"He puts on this persona like, ‘I’m partying, I’m drinking [or] whatever’ but he’s really super intelligent," Mahomes told Logan Paul during a recent episode of the "Impaulsive" podcast.
- What is Artificial General Intelligence (AGI), and why are people worried about it?
AGI refers to a machine or a software that can perform any intellectual task that a human can do. This includes reasoning, common sense, abstract thinking, background knowledge, transfer learning, ...
- Intelligent Vending Machines Market To Reach USD 86.3 Billion By 2032 | DataHorizzon Research
Request Sample Report: https://bit.ly/4bpT6fH Segmentation Overview: The intelligent vending machines market has been segmented into machine type, technology, product, application and region.
Go deeper with Google Headlines on:
Super-intelligent machines
[google_news title=”” keyword=”super-intelligent machines” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]