Results for "modeling mismatch"

Ensuring robots do not harm humans.

Intelligence emerges from interaction with the physical world.

Predicting disease progression or survival.

AI predicting crime patterns (highly controversial).

Quantifying financial risk.

AI applied to scientific problems.

Deep learning system for protein structure prediction.

Finding mathematical equations from data.

Modeling chemical systems computationally.

Competition arises without explicit design.

Emergence of conventions among agents.

Awareness and regulation of internal processes.

Existential risk from AI systems.

Internal representation of the agent itself.

Sudden jump to superintelligence.

Stored compute or algorithms enabling rapid jumps.

Accelerating safety relative to capabilities.

Inferring and aligning with human preferences.

System-level design for general intelligence.

The field of building systems that perform tasks associated with human intelligence—perception, reasoning, language, planning, and decision-making—via algori...

Risk threatening humanity’s survival.