Robotics researchers at Rensselaer Polytechnic Institute were able to get a robot to show a hint of self-awareness during an artificial intelligence test.
The details of the experiment, as reported by New Scientist, seem almost sinister if you don't take into account the subjects are machines.
Researchers told three robots they were going to be given a pill that would disable their ability to speak. No pills were actually administered, but the functionality was programmed into a button located on the robot.
The button was then pressed for two of the three robots, preventing them from answering when a researcher asked, "Which pill did you receive?"
In response to this question, the one robot with the ability to respond rose to its feet and said, "I don't know."
But of course, that's a contradiction. If the robot is able to speak, that means there's no way it could have actually been given the pill. A second later, the robot realizes this and says "Sorry, I know now. I was able to prove that I was not given a dumbing pill.”
And thus, man was overthrown.
While not hugely groundbreaking (other robots and programs have demonstrated forms of self-awareness before), the experiment does show a computer changing its preconceptions on the fly to solve a variation of a classic logic test, while also interacting with the outside world.
To put it in context, right now Siri can answer questions you ask it. But it cannot tell that you are on the verge of smashing your phone on the ground because it isn't giving you the answers you want.
Anyway, hopefully the robot council that takes over in 2020 is able to look past the whole "dumbing pill" thing and treat us well as subjects.