Results for "aligned agents"

Intelligence emerges from interaction with the physical world.

Physical form contributes to computation.

Robots learning via exploration and growth.

Learning without catastrophic forgetting.

No agent benefits from unilateral deviation.

Rules governing auctions.

Designing efficient marketplaces.

Decisions dependent on others’ actions.

System-level behavior arising from interactions.

Early signals disproportionately influence outcomes.

Internal representation of the agent itself.

Risk threatening humanity’s survival.

Existential risk from AI systems.

Tendency to gain control/resources.

Research ensuring AI remains safe.