Machine learning allows us to build tools and applications 
that were previously beyond the reach of even the most 
skillful software engineer. With these new capabilities, we 
can build most anything we want. But how should we use them? 
In this talk, I describe my personal perspective on this 
question. Forging a positive future means tackling many 
important global problems simultaneously including, but not 
limited to: minimizing climate change, dealing with the 
impacts of extreme weather events, monitoring the biosphere, 
ensuring an adequate food supply, and achieving global 
consensus. Machine learning can contribute materially to each 
of these challenges, and I will present an overview of some of 
the recent research in these areas. Finally, I address the 
potential risks and rewards of machine learning itself, as the 
risks of machine learning are as great as its potential 
rewards.