PromptRiskDBThreat intelligence atlas
AI Risk

Anthropomorphising systems can lead to overreliance and unsafe use

Anticipated risk: "Natural language is a mode of communication particularly used by humans. Humans interacting with CAs may come to think of these agents as human-like and lead users to place undue confidence in these agents. For example, users may falsely attribute human-like characteristics to CAs such as holding a coherent identity over time, or being capable of empathy. Such inflated views of CA competen- cies...

View related techniquesRead profile
AI Risk5. Human-Computer Interaction5.1 > Overreliance and unsafe use2 - Post-deployment

Record summary

A quick snapshot of what this page covers.

Techniques1Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Domain5. Human-Computer InteractionThe broad risk area this belongs to.

Risk profile

How this risk is described and categorized.

Anticipated risk: "Natural language is a mode of communication particularly used by humans. Humans interacting with CAs may come to think of these agents as human-like and lead users to place undue confidence in these agents. For example, users may falsely attribute human-like characteristics to CAs such as holding a coherent identity over time, or being capable of empathy. Such inflated views of CA competen- cies may lead users to rely on the agents where this is not safe."

Domain5. Human-Computer Interaction
Subdomain5.1 > Overreliance and unsafe use
Entity1 - Human
Intent2 - Unintentional
Timing2 - Post-deployment
CategoryRisk area 5: Human-Computer Interaction Harms
SubcategoryAnthropomorphising systems can lead to overreliance and unsafe use

Related techniques

Attack methods connected to this risk.

Suggested mitigations

Defenses that may help with related attacks.

No propagated mitigations. No defense is available through the connected attack methods.

Source

Research source for this risk, when available.