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

Outer Alignment

Center for Human-Compatible AI (CHAI)

Inner Alignment

Machine Learning (ML)

Coordination / Cooperation

Interpretability (ML & AI)

GPT

Myopia

Debate (AI safety technique)