Scientists teach robots to deceive humans.

What could go wrong? From Daily Mail:

It sounds like something straight out of Stanley Kubrick’s 2001: A Space Odyssey.

But, in a chilling echo of the computer Hal from the iconic film, scientists have developed robots that are able to deceive humans and even hide from their enemies.

An experiment by researchers at the Georgia Institute of Technology is believed to be the first detailed examination of robot deception.

The team developed computer algorithms that would let a robot ‘decide’ whether it should deceive a human or another robot and gave it strategies to give it the best chance of not being found out.

The development may alarm those who are concerned that robots who are able to practice deception are not safe to work with humans.

But researchers say that robots that are capable of deception will be valuable in the future, particularly when used in the military.

Robots on the battlefield with the power of deception will be able to successfully hide and mislead the enemy to keep themselves and valuable information safe.

‘Most social robots will probably rarely use deception, but it's still an important tool in the robot's interactive arsenal because robots that recognise the need for deception have advantages in terms of outcome compared to robots that do not recognise the need for deception,’ said the study's co-author, Alan Wagner, a research engineer at the Georgia Tech Research Institute.