alignment
정렬 · 정렬(얼라인먼트)
The area of AI research focused on making a model actually follow the goals and rules its developers and users intend, aiming to reduce the risk that a more capable model behaves in unintended ways.
AI Glossary
정렬 · 정렬(얼라인먼트)
The area of AI research focused on making a model actually follow the goals and rules its developers and users intend, aiming to reduce the risk that a more capable model behaves in unintended ways.