oversight
The process by which external actors or mechanisms observe, evaluate, constrain, or correct an AI system's behavior, especially during training, evaluation, or deployment, in order to detect problems and keep behavior within intended bounds.
Metadata
- aliases
- en
- AI oversight
- human oversight
- ja
- オーバーサイト
- 監視
- concept_id
- oversight
- preferred
- en
- oversight
- ja
- 監督
- relations
- relations
- broader
- related
- status
- active
Documents: mentions (2)
broader (1)
narrower (5)
prerequisite_of (6)
- alignment faking
- deceptive alignment
- iterated amplification
- scalable oversight
- trusted monitoring
- untrusted monitoring