MIT AI Risk Repository · Additional evidence · 16.05.02.a

Anthropomorphising systems can lead to overreliance and unsafe use

Category: Risk area 5: Human-Computer Interaction Harms

Description

From Taxonomy of Risks posed by Language Models (Weidinger2022), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Domain
Subdomain
Causal entity
Intent
Timing

Other entries from Weidinger2022