Completed
- The risks of learned optimization in advanced machine learning systems
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
State of the Industry - Short-Circuiting Reward Functions
Automatically move to the next video in the Classroom when playback concludes
- 1 - The risks of learned optimization in advanced machine learning systems
- 2 - The Inner Alignment Problem
- 3 - The dangers of self-optimizing machines
- 4 - The limitations of AI according to "The AI Alignment Problem"
- 5 - The Uncertainty of the World
- 6 - The importance of learning
- 7 - The dangers of hyperpalatable foods
- 8 - The cost of disentangling proximal from distal goals
- 9 - The goals of a superintelligence
- 10 - The possibility of an agent with a rich enough action space
- 11 - The dangers of a superintelligence
- 12 - The risks of a superintelligence intervening in goal information
- 13 - Flaws in the reasoning of superintelligence containment
