AI Alignment

Subfield of AI safety studying how to make AI systems' objectives match what humans intend.

Specifications & Metrics

type

Problems

Core Principles & Analysis

• A subfield of AI safety — the study of how to build safe AI systems.
• AI alignment refers to ensuring that an AI system's objectives match some target.
• Misalignment between objectives and target behavior is the field's central risk.

Sources

• Wikipedia: AI alignment