Good point. But at any given time, its doing EV calculations to decide its actions. Even if it modulates itself by picking amongst a variety of utility functions, its actions are still influenced by explicit EV calcs. If I understand TurnTrout’s work correctly, that alone is enough to make the agent power seeking. Which is dangerous by default.
Good point. But at any given time, its doing EV calculations to decide its actions. Even if it modulates itself by picking amongst a variety of utility functions, its actions are still influenced by explicit EV calcs. If I understand TurnTrout’s work correctly, that alone is enough to make the agent power seeking. Which is dangerous by default.