3 Principles for Creating Safer AI

A talk by Stuart Russel discussing principles to achieve human-compatible AI:

1. The robot’s only objective is to maximize the realization of human values.
2. The robot is initially uncertain about what those values are.
3. Human behavior provides information about human values.

We had better be quite sure that the purpose put into
the machine is the purpose which we really desire.

Norbert Wiener