Tags similar to: AI

GPT

Inner Alignment

Mesa-Optimization

Research Agendas

Outer Alignment

World Optimization

Machine Learning (ML)

Embedded Agency

Interpretability (ML & AI)

Infra-Bayesianism

Decision Theory

Language Models

Iterated Amplification

Goal-Directedness

Instrumental Convergence

Existential Risk

Impact Regularization

Reinforcement Learning