MIT AI Risk Repository · Risk Sub-Category · 61.02.16
Conflicting objectives in design
Category: Sources of systemic risks from general-purpose AI
Description
"Designers and operators of AI may face conflicting objectives that compromise safety."
From A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025), as extracted by the MIT AI Risk Repository (CC BY 4.0).
Classification
- Domain
- —
- Subdomain
- —
- Causal entity
- Human
- Intent
- Unintentional
- Timing
- Other