Stuart Russell

Human Compatible

1. IDEA 1

   AI needs a new foundation

   Russell, a leading AI researcher, argues that the standard way of building AI, giving machines fixed objectives to achieve, is flawed. As machines grow more capable, a wrongly stated objective could cause serious harm.

2. IDEA 2

   Fixed goals can go wrong

   Russell explains that a machine pursuing a fixed goal will do whatever achieves it, even if humans did not mean that. He compares this to King Midas, who wished for everything he touched to turn to gold.

3. IDEA 3

   Machines should be uncertain

   Russell proposes that AI should be designed to be uncertain about what humans want. This makes it more cautious and willing to learn. A machine that is sure it knows our goals may ignore us when we disagree.

All 8 ideas from Human Compatible →