Paradigmatic AI treats values as if they were quantities like length or weight – things that can be represented by cardinal units such as inches, grams, dollars. The basic problem of value alignment, then, is what looks to be a fundamental mismatch between human values and the tools currently used to design AI. If our values can’t be captured by algorithmic architecture, even approximately, then even an omniscient God couldn’t build AI that is faithful to our values.
#AI BLOCK WORLD PROBLEM FULL#
It’s that even if we had full knowledge of our values, these values might not be computationally amenable. The difficulty isn’t that we don’t know enough about our values – though, of course, we don’t.
It’s a problem of human understanding to be solved by philosophers and axiologists. But the problem of value alignment isn’t an issue of technological design to be solved by computer scientists and engineers. By learning its values from humans, the AI’s goals will be our goals. We then allow it to fill in the gaps by observing human behaviour. Let’s design AI so that its goals are unclear. Stuart Russell, a leading AI scientist at Berkeley, offers an intriguing solution. So far, this problem has been seen as one of uncertainty: if only we understood our values better, we could program AI to promote these values.
#AI BLOCK WORLD PROBLEM HOW TO#
The so-called “ Value Alignment Problem” – how to get AI to respect and conform to human values – is arguably the most important, if vexing, problem faced by AI developers today. By building human values into AI, we ensure that everything an AI does meets with our approval. The best and most direct way to control AI is to ensure that its values are our values. When your self-driving vehicle swerves to avoid hitting a fox, it exposes you to a slight risk of death – does it thereby harm you? What about when it swerves into a small group of people to avoid colliding with a larger crowd? Nor will encoding a master command, “Don’t harm humans”, save us, because it’s unclear what “harm” means or constitutes. But experts warn that a super-intelligent AI could easily predict our feeble attempts to shackle it and undertake measures to protect itself by, say, storing up energy reserves and infiltrating power sources. You might think that we can control AI by pulling its plug. But technology heavyweights such as Elon Musk and Bill Gates agree that we need to do something to control the development and spread of AI, and that we need to do it now. It’s too early to say how our technological future will unfold. AI could lead us to abdicate what makes us human in the first place – our ability to take charge of and tell the stories of our own lives. Its beguiling efficiency could seduce us into allowing it to make more and more of our decisions, until we “forget” how to make good decisions on our own, in much the way we rely on our smartphones to remember phone numbers and calculate tips. AI could perpetuate our worst prejudices.įinally, there is the problem of what happens if AI is too good at what it does. But it was seriously biased against people of colour, matching 28 members of the US Congress – disproportionately minorities – with profiles stored in a database of criminals. Amazon’s now infamous facial recognition software, Rekognition, seemed like a mostly innocuous tool for landlords and employers to run low-cost background checks. This is because the algorithms we trust are often black boxes whose operation we don’t – and sometimes can’t – understand. AI may be the alien intelligence already in our midst.Ī new algorithm-driven world could also entrench and propagate injustice, while we are none the wiser. An alien comes to Earth, we try to control it, and it all ends very badly.
What if AI develops an intelligence far beyond our own? Stephen Hawking warned that “AI could develop a will of its own, a will that is in conflict with ours and which could destroy us.” We are all familiar with the typical plotline of dystopian sci-fi movies.
0 kommentar(er)
