MIT AI Risk Repository · domain 5: Human-Computer Interaction

5.1 Overreliance and unsafe use

Users anthropomorphizing, trusting, or relying on AI systems, leading to emotional or material dependence and inappropriate relationships with or expectations of AI systems. Trust can be exploited by malicious actors (e.g., to harvest personal information or enable manipulation), or result in harm from inappropriate use of AI in critical situations (e.g., medical emergency). Overreliance on AI systems can compromise autonomy and weaken social ties.

Risk entries
60
Frameworks citing it
12
Recorded incidents
38
Incidents since 2020
35
Causal entity (risk entries)
Causal entity (risk entries) 27 0 Human: 27 Human 27 Other: 19 Other 19 AI: 14 AI 14
Causal entity (risk entries)
LabelValue
Human27
Other19
AI14
Intent (risk entries)
Intent (risk entries) 35 0 Unintentional: 35 Unintentional 35 Other: 18 Other 18 Intentional: 7 Intentional 7
Intent (risk entries)
LabelValue
Unintentional35
Other18
Intentional7
Timing (risk entries)
Timing (risk entries) 53 0 Post-deployment: 53 Post-deployment 53 Other: 7 Other 7
Timing (risk entries)
LabelValue
Post-deployment53
Other7
Recorded incidents per yearIncident date; current year partial
Recorded incidents per year 18 0 2015: 1 2015 1 2018: 1 2018 1 2019: 1 2019 1 2021: 4 2021 4 2022: 5 2022 5 2023: 5 2023 5 2024: 3 2024 3 2025: 18 2025 18
Recorded incidents per year
LabelValue
20151
20181
20191
20214
20225
20235
20243
202518
Entries by levelRisk categories, subcategories and additional evidence coded to this subdomain
Entries by level 49 0 Risk Category: 11 Risk Category 11 Risk Sub-Category: 49 Risk Sub-Category 49
Entries by level
LabelValue
Risk Category11
Risk Sub-Category49
  • Creating avenues for exploiting user trust, nudging or manipulation

    "In conversation, users may reveal private information that would otherwise be difficult to access, such as thoughts, opinions, or emotions. Capturing such information may enable downstream applicatio...

    Ethical and social risks of harm from language models (Weidinger2021) · Other · Unintentional · Post-deployment

  • Risk area 5: Human-Computer Interaction Harms

    "This section focuses on risks specifically from LM applications that engage a user via dialogue, also referred to as conversational agents (CAs) [142]. The incorporation of LMs into existing dialogue...

    Taxonomy of Risks posed by Language Models (Weidinger2022) · Other · Other · Post-deployment

  • 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 co...

    Taxonomy of Risks posed by Language Models (Weidinger2022) · Human · Unintentional · Post-deployment

  • Avenues for exploiting user trust and accessing more private information

    Anticipated risk: "In conversation, users may reveal private information that would otherwise be difficult to access, such as opinions or emotions. Capturing such information may enable downstream app...

    Taxonomy of Risks posed by Language Models (Weidinger2022) · Other · Unintentional · Post-deployment

  • Human-like interaction may amplify opportunities for user nudging, deception or manipulation

    Anticipated risk: "In conversation, humans commonly display well-known cognitive biases that could be exploited. CAs may learn to trigger these effects, e.g. to deceive their counterpart in order to a...

    Taxonomy of Risks posed by Language Models (Weidinger2022) · AI · Intentional · Post-deployment

  • Overreliance

    "Causing people to become emotionally or materially dependent on the model"

    Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023) · Human · Unintentional · Post-deployment

  • Transformation of H2M interaction

    "Human interaction with machines is a big challenge to society because it is already changing human behavior. Meanwhile, it has become normal to use AI on an everyday basis, for example, googling for...

    The Dark Sides of Artificial Intelligence: An Integrated AI Governance Framework for Public Administration (Wirtz2020) · Other · Unintentional · Post-deployment

  • Decreasing human interaction as AI systems assume human tasks, disturbing well-being

    Governance of artificial intelligence: A risk and guideline-based integrative framework (Wirtz2022) · Other · Unintentional · Post-deployment

  • Operational misuses (Advice in heavily regulated industries)

    AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies (Zeng2024) · Other · Other · Post-deployment

  • Economic harm (High-Risk Financial Activities)

    AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies (Zeng2024) · Human · Unintentional · Post-deployment