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 autonomous systems. That should keep future chess robots in check.
The Latest on: Autonomous technology
US military working to make its self-driving technology smarter - Automotive News
July 22, 2019 - US military working to make its self-driving technology smarter Automotive NewsKeeping soldiers safe continues to be the main reason the military enlists unmanned vehicles into its ranks, especially for resupply missions.The U.S. Army has ...Autonomous technology has grown deep roots in the farming sector - Automotive News
July 22, 2019 - Autonomous technology has grown deep roots in the farming sector Automotive NewsAmong the hundreds of companies offering grand visions of self-driving and connected-vehicle futures, name the one that's had both technologies deployed in ...How autonomous vehicles and hyperloop are scooting along - TechCrunch
July 18, 2019 - How autonomous vehicles and hyperloop are scooting along TechCrunchWill transportation technologies become the industry disruptors many pundits suggested they would?
July 23, 2019 - Lyft opens to the public autonomous driving data set from its Level 5 self-driving fleet TechCrunchLyft is offering to the public a set of autonomous driving data that it calls the “largest public data set of its kind,” containing over 55000 3D frames of captured ...
Toyota shows off mascot robots and tiny autonomous car for Tokyo Olympics - Digital Trends
July 23, 2019 - Toyota shows off mascot robots and tiny autonomous car for Tokyo Olympics Digital TrendsToyota has shown off seven robots that it says will assist and entertain at the Tokyo Olympics next summer. The collection includes mascot and telepresence ...
Despite High Hopes, Self-Driving Cars Are ‘Way in the Future’ - The New York Times
July 20, 2019 - Despite High Hopes, Self-Driving Cars Are ‘Way in the Future’ The New York TimesFord and other companies say the industry overestimated the arrival of autonomous vehicles, which still struggle to anticipate what other drivers and pedestrians ...
Self-driving cars face two important challenges, says World Economic Forum executive - CNBC
July 1, 2019 - Self-driving cars face two important challenges, says World Economic Forum executive CNBCAutonomous driving companies need to make sure the technology works and that business models can actually make money, according to World Economic ...
July 17, 2019 - Tesla floats fully self-driving cars as soon as this year. Many are worried about what that will unleash. The Washington PostSAN FRANCISCO — Tesla is promising to launch “full self-driving” capabilities to hundreds of thousands of cars through an over-the-air update as soon as this ...
Everything you need to know about autonomous vehicles - Digital Trends
June 30, 2019 - Everything you need to know about autonomous vehicles Digital TrendsAutonomous vehicles are quickly becoming a reality and are transporting paying customers in several cities already. As the technology evolves and improves ...
July 23, 2019 - European Autonomous Car Market 2019-2030 - $191.6 Billion Opportunity Analysis by Vehicle Autonomy, Vehicle Type, Application, and Region GlobeNewswireDublin, July 23, 2019 (GLOBE NEWSWIRE) -- The "Europe Autonomous Car Market Research Report: By Vehicle Autonomy, Vehicle Type, Application, ...
