Although the original vision for artificial intelligence was the simulation of (implicitly human) intelligence, research has gradually shifted to autonomous systems that compete with people. The resultant popular attitude toward artificial intelligence, we argue here, is by turns disdain, grudging acceptance, and fear. That attitude not only limits our work's potential, but also imperils its support. This paper proposes a constructive alternative: the development of collaborative intelligence. As envisioned here, a collaborative intelligence does not require encyclopedic command and need not be limited to a single problem. The necessary components of a collaborative intelligence are nearly at hand, and the key issues readily identified. As a first step, this paper proposes three challenging but accessible problems that would both change the public perception of artificial intelligence and spur substantive research to advance our science.
