Tags similar to: Myopia

AI

Decision Theory

Self Fulfilling/Refuting Prophecies

Instrumental Convergence

AI Success Models

Hansonian Pre-Rationality

Parables & Fables

Research Agendas

Inner Alignment

Debate (AI safety technique)

Iterated Amplification

Outer Alignment

Interpretability (ML & AI)

Machine Learning (ML)

GPT

Mesa-Optimization

Bounties (closed)

Market making (AI safety technique)

LessWrong Review

Eliciting Latent Knowledge (ELK)

Counterfactuals