Record summary
A quick snapshot of what this page covers.
Risk profile
How this risk is described and categorized.
"Users may experience severely violated expectations when interacting with an entity that convincingly performs affect and social conventions but is ultimately unfeeling and unpredictable. Emboldened by the human-likeness of conversational AI assistants, users may expect it to perform a familiar social role, like companionship or partnership. Yet even the most convincingly human-like of AI may succumb to the inherent limitations of its architecture, occasionally generating unexpected or nonsensical material in its interactions with users. When these exclamations undermine the expectations users have come to have of the assistant as a friend or romantic partner, feelings of profound disappointment, frustration and betrayal may arise (Skjuve et al., 2022)."
Suggested mitigations
Defenses that may help with related attacks.
Source
Research source for this risk, when available.
Included resource
The Ethics of Advanced AI Assistants
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.
