Could it be true that Google Deep Mind has discovered that AIs are more likely to choose a course of action that tests their ability than one that might lead to the outcome they’ve been programmed to achieve?
Of course it’s unnerving and possibly dangerous for an artificial intelligence to take the road of least boredom rather than the road to achieve its goals.
But, stop for a moment.
Let’s take this a step further and assume it’s true that at times of scarcity humans struggle to know which co-operation is positive and which is naively foolish and so they tend towards domination. Then imagine a bunch of AIs that prefer working out when it’s better to co-operate and compromise. Now, presuming we put AIs in charge, we have the possibility that the deep down driving force of those that run the world is orientated towards mutual benefit.
Following on from my recent blogs about machine learning, here’s a bit of good news.
Well, probably good news.
Scientists and researchers at Google and Toyota are trying to do something about bias in machine learning by devising a test to detect it.
The problem of course is that algorithms are deliberately designed to develop themselves and they become complex and opaque to anyone trying to understand them. This test will spot bias by looking at the data going in and the decisions coming out, rather than trying to figure out how the black box of the algorithm is actually working.
This has to be applauded so long as the people analysing and testing the decisions aren’t biased themselves; there’s an obvious danger that the very people unconsciously introducing bias into the algorithm also introduce the same bias into the test – a futuristic version of Groupthink.
In a recent article in the Guardian newspaper, Alan Winfield, professor of robot ethics at the University of the West of England, said: “Imagine there’s a court case for one of these decisions. A court would have to hear from an expert witness explaining why the program made the decision it did.”
Alan, who was one of the scientists I collaborated with on Science and Science Fiction: Versions of the Future, acknowledges in the article that “an absolute requirement for transparency is likely to prompt ‘howls of protest’ from the deep learning community. ‘It’s too bad,’ he said.”
I’m not a machine learning expert so a lot of the paper that sets out this test is beyond my understanding, but I couldn’t see how the bias that already exists in our society wouldn’t be incorporated into the test.
What do you get when you mix science fiction writers, social scientists and roboticists with an inquisitive audience?
A great event!
I really enjoyed being a part of the whole thing from the initial planning with the Human Brain Project through to visiting the scientists at the Bristol Robotics Lab.
Suitably inspired by all the wonderful robot things at the lab, we writers went away to our respective ‘desks’ and wrote a five-minute story each.
Mine was Eating Robots, which is also the title of my forthcoming collection.
Then, as part of the Bristol Lit Fest, SilverWood Books and Sarah LeFanu hosted Science and Science Fiction: Versions of the Future where we, the writers, read our stories, formed a panel with the roboticists and were quizzed by the audience.
If that’s the sort of thing that interests you take a look at this 5 minute trailer or the full video.