Results for "learned objectives"

Emergent Coordination Intermediate

Coordination arising without explicit programming.

AI Economics & Strategy

Mode Collapse Advanced

Generator produces limited variety of outputs.

Diffusion & Generative Models

Hierarchical Planning Advanced

Decomposing goals into sub-tasks.

Agents & Autonomy

Robust Alignment Advanced

Maintaining alignment under new conditions.

AI Safety & Alignment

Change Management Intermediate

Governance of model changes.

Governance & Ethics

Model Orchestration Intermediate

Coordinating models, tools, and logic.

AI Economics & Strategy

Token Budgeting Intermediate

Limiting inference usage.

AI Economics & Strategy

Plant Intermediate

The physical system being controlled.

Foundations & Theory

Cooperative Game Advanced

Agents optimize collective outcomes.

Agents & Autonomy

Existential Risk Advanced

Risk threatening humanity’s survival.

AI Safety & Alignment

Shutdown Problem Advanced

Ensuring AI allows shutdown.

AI Safety & Alignment

Power-Seeking Behavior Advanced

Tendency to gain control/resources.

AI Safety & Alignment

Orthogonality Thesis Advanced

Intelligence and goals are independent.

AI Safety & Alignment

Instrumental Goals Advanced

Goals useful regardless of final objective.

AI Safety & Alignment

Alignment Research Intermediate

Research ensuring AI remains safe.

Governance & Ethics

Cooperative AI Intermediate

Designing AI to cooperate with humans and each other.

Governance & Ethics