Ray Kurzweil: We Can Control AI Before It Controls Us

Over time, technology offers solutions to old problems while creating new issues in the process. The more powerful the technology, the greater its potential to do good and harm. Artificial intelligence is no exception, and as AI has advanced, worry about its risks has grown too.

Technology’s dual identity isn’t new, Ray Kurzweil said in a Q&A at Singularity University.

This cycle of excitement and worry is normal for new technologies. When a technology is first developed, we dream about the good it might do, and as it matures, we worry about unforeseen risks. Taking both sides into account, Kurzweil said he comes out cautiously optimistic. He acknowledges there’s risk, and suggests the answer isn’t to halt progress, but to plan for it.

By creating safeguards and standards in advance, we can better defend against negative consequences. As an example, Kurzweil points to the 1975 Asilomar Conference, a meeting that sought to define the ethical boundaries of biotech research before it reached its full potential. He believes a similar approach might work for AI and other exponential technologies.

As our technologies change the world, the responsibility only grows deeper for each of us to take an active role in shaping it the way we want—not the other way around.