
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 Doesn’t Pose an Existential Risk—but Silicon Valley Does
More than 350 executives, engineers, and researchers who work on AI have signed a pithy one-sentence statement: “Mitigating the risk of extinction from AI should be a global priority alongside other ...
- Becoming ungovernable: Is AI regulation even feasible?
The heat is coming on policymakers, as yet another plea is made by AI developers to regulate the technology. Last week, Sam Altman, Geoffrey Hinton, and a cast of thousands have issued yet another ...
- ⚠️ AI leaders warn: ‘Risk of extinction’
Let me say it another way … The very same people who created AI are saying that AI can wipe out humanity. The signed statement is a who’s who of tech pioneers: Elon Musk, Sam Altman (CEO of OpenAI, ...
- AI doom, AI boom and the possible destruction of humanity
Will AI solve complex problems and save us? Or will it obfuscate truth, destroying humanity? Like any paradox, the answer is unclear.
- Commentary: No, artificial intelligence probably won't kill us all
Framing artificial intelligence as an existential threat is merely a doomsaying tactic. There may be more to this fear campaign than meets the eye, says this researcher.
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
- Just a few of the cool cars and machines you can see when ‘Rise Of The Beasts’ charity roadtrip starts tomorrow morning
THE wait is over and Bumblebee 1000’s ‘Rise Of The Beasts’ charity road trip blasts off tomorrow at Barberstown Castle, Kildare from 8:45am. There will be 100 supercars taking part, and to whet ...
- Robot farmers? Machines are crawling through America's fields. And some have lasers.
“It’s been quite a change,” said Luis Vargas, who started out on 20-person weeding crews in high school and now runs a fleet of four robot weeders for Tanimura & Antle, a grower and seller of fresh ...
- Why are the people who pushed for artificial intelligence now signing so many doomsday manifestos?
In recent weeks, the creators of this technology and the sector’s big investors, along with thousands of academics, have been warning about the extraordinary dangers of AI ...
- The AI Apocalypse Is Here - - What Will Stop AI from Destroying Us?
OvalPixel's new AI trivia game is powered by the same technologies that could enable super intelligent machines—but applied in a way that's safe, ethical, and fun. The blockchain-based game ...
- The AI Apocalypse Is Here - - What Will Stop AI from Destroying Us?
Egbuonu may be onto something. OvalPixel's new AI trivia game is powered by the same technologies that could enable super intelligent machines—but applied in a way that's safe, ethical ...
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”]