Nick Bostrom mathematically argues that an agent’s intelligence level and its ultimate goals are orthogonal vectors. Highly sophisticated cognitive systems can possess completely arbitrary objective functions.
Part of the 26 Structural Foundations: How We Teach Machines to Understand Purpose and Human Intent archive. HistoricallyVerified
Top 5 Structural Foundations: Pure Intent
- Gradient Ascent Optimization — Augustin-Louis Cauchy introduces gradient methods to find local extrema via iterative steps along th...
- The Objective Function Shift — Mathematical programming formalizes the objective function as the explicit mathematical expression o...
- Rational Agency Axioms — Stuart Russell and Peter Norvig define the ideal rational agent as an architecture that acts to maxi...
- The Art of Saying Nothing: The Rare Power of Shared Silence — We live in a world that treats silence like a system error. The moment a conversation pauses, panic...
- Why I Stopped Trusting Smiling People at Work: The Toxic Corporate Mask — You walk into the office and there they are. The perfectly rehearsed, flashing white smiles. From t...
Discussion: