AI Alignment & Safety

Topics

• 01The Alignment Problem
• 02Specification Gaming
• 03Reward Hacking
• 04Interpretability for Safety
• 05Scalable Oversight
• 06Robustness & Adversarial Examples
• 07Evaluations & Red Teaming
• 08Deceptive Alignment
• 09Existential Risk Arguments
• 10Corrigibility

Also covered elsewhere

This subject genuinely sits in more than one domain. These fields approach the same ground with different methods.

• PhilosophyApplied EthicsMoral philosophy where the stakes are concrete.
• Artificial IntelligenceAI Ethics, Policy & SocietyWho is accountable when the model is wrong.

Elsewhere in Artificial Intelligence

• Machine Learning Foundations
• Deep Learning
• Natural Language Processing
• Computer Vision
• Reinforcement Learning
• Generative Models