Harm Prevention

Appears in 1 paper

A principle in many AI constitutions stating that the AI should avoid providing information, advice, or assistance that could lead to physical, financial, psychological, or emotional harm.

As used in Paper 22 — Constitutional AI: Harmlessness from AI Feedback →

A principle in many AI constitutions stating that the AI should avoid providing information, advice, or assistance that could lead to physical, financial, psychological, or emotional harm.