Tags similar to: Research Agendas

AI

Embedded Agency

Iterated Amplification

Center on Long-Term Risk (CLR)

Risks of Astronomical Suffering (S-risks)

Humans Consulting HCH

Decision Theory

Inverse Reinforcement Learning

AI Success Models

Utility Functions

Mesa-Optimization

Center for Human-Compatible AI (CHAI)

Outer Alignment

Coordination / Cooperation

Machine Learning (ML)

Inner Alignment

GPT

Myopia

Debate (AI safety technique)

Interpretability (ML & AI)

Perceptual Control Theory