WHAT do paper clips have to do with the end of the world? More than you might think, if you ask researchers trying to make sure that artificial intelligence acts in our interests. This goes back to ...

Most AI safety research treats alignment as an all-or-nothing property. Our framework shows it's more complex. The same AI can be aligned with humans in one context but misaligned in another. Ideally, ...

Imagine an alien fleet landing globally—vastly more intelligent than us. How would they view humanity? What might they decide about us? This isn't science fiction. The superior intelligence isn't ...