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:
- Kids! Don’t Try This At Home! Robot Destroys Mankindon April 27, 2021 at 4:59 pm
[Elon Musk], [Bill Gates], [Steve Wozniak], and [Stephen Hawking] have all gone on record warning us that artificial intelligence is dangerous. I’ll grant you, all of those people must be ...
- The Morning After: The end of the line for Harmony remoteson April 10, 2021 at 9:41 pm
to passable (the way current devices link to AI tech and your smartphone), but if there’s ... this week’s surprising news around muons and why believes we’ll eventually unite with superintelligent ...
- The Morning After: The end of the line for Harmony remoteson April 10, 2021 at 8:08 am
to passable (the way current devices link to AI tech and your smartphone), but ... muons and why believes we’ll eventually unite with superintelligent robots and roam the cosmos as beings ...
- The future of AI is being shaped right now. How should policymakers respond?on April 8, 2021 at 7:44 am
let alone a superintelligent one. And for a while — in the ’60s, ’70s, and ’80s — it seemed like such speculation would remain just that. The sluggishness of AI development actually gave ...
- 'Ex Machina' director embraces the rise of superintelligent AIon March 31, 2021 at 5:00 pm
Now, with his directorial debut, Ex Machina, Garland is taking on artificial intelligence -- and in the process, he shows the limits of the Turing test, the most common method for determining if ...
Go deeper with Google Headlines on:
Go deeper with Bing News on:
- Intelligence In Motion: Predicting The Next Supply Chain Disruptionon April 30, 2021 at 10:31 am
Downstream impacts; All kinds of events will disrupt supply chains. getty. I recently had the opportunity to deliver the keynote at Demand Driven Technologies’ Global Conference ...
- NETFLIX Review: 'The Mitchells vs. The Machines' is fully-charged and connectedon April 30, 2021 at 7:46 am
Beautifully animated, hilarious and inventive, "The Mitchells vs. The Machines" is exactly what you'd expect from "The LEGO Movie" directing duo, Phil Lord and Christopher ...
- The Computers Are Getting Better at Writingon April 30, 2021 at 3:00 am
The changes that are coming are fundamental to every method of speaking and writing that presently exists. Amit Gupta is one of the founders of Sudowrite. He left Silicon Valley for a career as a ...
- You’ve Decided to Adopt RPA. Now What?on April 29, 2021 at 11:50 am
Here’s a breakdown of automation hierarchies and what CFOs should know about them.
- Artificial intelligence must not be allowed to replace the imperfection of human empathyon April 29, 2021 at 1:31 am
Instead of a human ruling “master race”, we could end up with a machine one. If this seems extreme, consider the anti-human perfectionism that is already central to the labour market. Here, AI ...