Preventing AI from developing anti-social and potentially harmful behaviour

Apr 17, 2014

Next time you play a computer at chess, think about the implications if you beat it. It could be a very sore loser!

A study just published in the Journal of Experimental & Theoretical Artificial Intelligence reflects upon the growing need for autonomous technology, and suggests that humans should be very careful to prevent future systems from developing anti-social and potentially harmful behaviour.

Modern military and economic pressures require autonomous systems that can react quickly – and without human input. These systems will be required to make rational decisions for themselves.

Researcher Steve Omohundro writes: "When roboticists are asked by nervous onlookers about safety, a common answer is 'We can always unplug it!' But imagine this outcome from the chess robot's point of view. A future in which it is unplugged is a future in which it cannot play or win any games of chess".

Like a plot from The Terminator movie, we are suddenly faced with the prospect of real threat from autonomous systems unless they are designed very carefully. Like a human being or animal seeking self-preservation, a rational machine could exert the following harmful or anti-social behaviours:

  • Self-protection, as exampled above.
  • Resource acquisition, through cyber theft, manipulation or domination.
  • Improved efficiency, through alternative utilisation of resources.
  • Self-improvement, such as removing design constraints if doing so is deemed advantageous.

The study highlights the vulnerability of current autonomous systems to hackers and malfunctions, citing past accidents that have caused multi-billion dollars' worth of damage, or loss of human life. Unfortunately, the task of designing more rational systems that can safeguard against the malfunctions that occurred in these accidents is a more complex task that is immediately apparent:

"Harmful systems might at first appear to be harder to design or less powerful than safe systems. Unfortunately, the opposite is the case. Most simple utility functions will cause harmful behaviour and it is easy to design simple utility functions that would be extremely harmful."

This fascinating study concludes by stressing the extreme caution that should be used in designing and deploying future rational technology. It suggests a sequence of provably safe systems should first be developed, and then applied to all future . That should keep future chess robots in check.

Explore further: If you want to trust a robot, look at how it makes decisions

More information: "Autonomous technology and the greater human good", by Steve Omohundro, Journal of Experimental & Theoretical Artificial Intelligence, published by Taylor & Francis. DOI: 10.1080/0952813X.2014.895111

add to favorites email to friend print save as pdf

Related Stories

Making robots more trustworthy

Jul 03, 2013

Researchers from the University of Hertfordshire are part of a new £1.2 million project that aims to ensure that future robotic systems can be trusted by humans.

Recommended for you

Coping with floods—of water and data

Dec 19, 2014

Halloween 2013 brought real terror to an Austin, Texas, neighborhood, when a flash flood killed four residents and damaged roughly 1,200 homes. Following torrential rains, Onion Creek swept over its banks and inundated the ...

Cloud computing helps make sense of cloud forests

Dec 17, 2014

The forests that surround Campos do Jordao are among the foggiest places on Earth. With a canopy shrouded in mist much of time, these are the renowned cloud forests of the Brazilian state of São Paulo. It is here that researchers ...

User comments : 0

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.