MIT AI Risk Repository · Risk Category · 42.18.00

Interpretability

Open the MIT Risk Navigator All entries from Teixeira2022

Description

"Describe the internals of a system in a way that is understandable to humans."

From An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance (Teixeira2022), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Domain: —
Subdomain: —
Causal entity: Not coded
Intent: Not coded
Timing: Not coded

Other entries from Teixeira2022

Accountability Risk Category · 7.4
Manipulation Risk Category · 4.1
Accuracy Risk Category · 7.3
Moral Risk Category · 7.3
Bias Risk Category · 1.1
Opacity Risk Category · 7.4
Completeness Risk Category
Power Risk Category · 6.1
Data Protection/Privacy Risk Category · 2.1
Extintion Risk Category · 7.2
Protection Risk Category · 7.3
Security Risk Category · 4.2