Domain: Governance & Ethics

27 terms

AI Center of Excellence Intermediate

Centralized AI expertise group.
AI Treaty Intermediate

International agreements on AI.
Alignment Research Intermediate

Research ensuring AI remains safe.
Audit Intermediate

Systematic review of model/data processes to ensure performance, fairness, security, and policy compliance.
Auditability Intermediate

Ability to inspect and verify AI decisions.
Change Management Intermediate

Governance of model changes.
Compute Governance Intermediate

Regulating access to large-scale compute.
Cooperative AI Intermediate

Designing AI to cooperate with humans and each other.
Data Protection Impact Assessment Intermediate

Privacy risk analysis under GDPR-like laws.
Differential Progress Intermediate

Accelerating safety relative to capabilities.
EU AI Act Intermediate

European regulation classifying AI systems by risk.
Explainability Mandate Intermediate

Requirement to provide explanations.
High-Risk AI System Intermediate

AI used in sensitive domains requiring compliance.
Incident Response Intermediate

Process for managing AI failures.
ISO/IEC 23894 Intermediate

International AI risk standard.
Kill Switch Intermediate

Mechanism to disable AI system.
Model Documentation Intermediate

Required descriptions of model behavior and limits.
Model Governance Intermediate

Policies and practices for approving, monitoring, auditing, and documenting models in production.
Model Release Control Intermediate

Restricting distribution of powerful models.
Model Tiering Intermediate

Classifying models by impact level.
NIST AI RMF Intermediate

US framework for AI risk governance.
Responsible AI Intermediate

A discipline ensuring AI systems are fair, safe, transparent, privacy-preserving, and accountable throughout lifecycle.
Risk Register Intermediate

Central log of AI-related risks.
Shadow AI Intermediate

AI used without governance approval.
Transparency Obligation Intermediate

Requirement to inform users about AI use.
Use Case Approval Intermediate

Review process before deployment.
Value Learning Intermediate

Inferring and aligning with human preferences.