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
[google_news title=”” keyword=”Autonomous technology” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Autonomous technology
- Refrigerated Fast Food Is Getting Autonomous Rides from Dallas to Oklahoma Cityon March 1, 2024 at 11:31 am
Want fries with that? If you do—and you're in Oklahoma City—they may have just gotten a robotically driven truck ride from Dallas before getting plopped in a fryer and placed in your fast food bag.
- Exploring Autonomous Navigation for Lunar Excavator Missionson March 1, 2024 at 10:30 am
These factors complicate the navigation process, but NASA’s IPEx team is proactively tackling these issues. They’ve initiated a series of tests focusing on autonomous driving technology, performed ...
- Autonomous vehicle technology vulnerable to road object spoofing and vanishing attackson March 1, 2024 at 7:32 am
A University of California, Irvine-led research team has demonstrated the potentially hazardous vulnerabilities associated with the technology called LiDAR, or Light Detection and Ranging, many ...
- STEER Tech CEO sees opportunity for innovation ahead in autonomous vehicle partnerships with smart citieson March 1, 2024 at 6:03 am
STEER Tech specializes in low-speed and off-road applications commonly found supporting commercial fleet companies.
- The Speed Of Technology: Short Versus Long-Term Impactson March 1, 2024 at 6:00 am
Over time, self-driving technology became more refined and reliable. Pilot programs and public demonstrations showcased the capabilities of autonomous vehicles, gradually building confidence among ...
- Summit inspires Pittsburgh to take lead in health care safety again through technologyon February 29, 2024 at 12:10 pm
Pittsburgh can lead the charge to make health care safer by flowing in innovations in robotics, AI and other technology — and the Jewish Healthcare Foundation, the Pittsburgh Regional Health ...
- Oracle’s autonomous database goes distributed and globalon February 29, 2024 at 6:01 am
The Distributed Autonomous Database is a single logical database management system horizontally partitioned or sharded. Each shard is an independent database instance that hosts a subset of the ...
- Apple Abandons Plans for Driverless Electric Car, Shifts Team to AIon February 28, 2024 at 11:50 am
While a disappointment to green-tech supporters, Apple's decision reflects the growing uncertainty in the E.V. market.
- Hyundai-backed autonomous company Motional cuts 5% of workforceon February 28, 2024 at 9:56 am
Motional, the autonomous vehicle startup backed by Hyundai, is laying off about 5% of its workforce, according to sources.
- Apple ramped up its autonomous car project last year. Now, it’s killing it.on February 27, 2024 at 9:17 pm
Apple reportedly scales back autonomous car project, despite aggressively ramping up testing over the past year in California. The company still has 67 active test permits in the state.
via Bing News