MIT AI Risk Repository · domain 7: AI system safety, failures, & limitations

7.3 Lack of capability or robustness

AI systems that fail to perform reliably or effectively under varying conditions, exposing them to errors and failures that can have significant consequences, especially in critical applications or areas that require moral reasoning.

Risk entries
126
Frameworks citing it
12
Recorded incidents
305
Incidents since 2020
207
Causal entity (risk entries)
Causal entity (risk entries) 81 0 AI: 81 AI 81 Human: 22 Human 22 Other: 20 Other 20 Not coded: 3 Not coded 3
Causal entity (risk entries)
LabelValue
AI81
Human22
Other20
Not coded3
Intent (risk entries)
Intent (risk entries) 89 0 Unintentional: 89 Unintentional 89 Other: 28 Other 28 Intentional: 6 Intentional 6 Not coded: 3 Not coded 3
Intent (risk entries)
LabelValue
Unintentional89
Other28
Intentional6
Not coded3
Timing (risk entries)
Timing (risk entries) 64 0 Post-deployment: 64 Post-deployment 64 Other: 32 Other 32 Pre-deployment: 27 Pre-deployment 27 Not coded: 3 Not coded 3
Timing (risk entries)
LabelValue
Post-deployment64
Other32
Pre-deployment27
Not coded3
Recorded incidents per yearIncident date; current year partial
Recorded incidents per year 37 0 2012: 3 2012 3 2013: 3 2013 3 2014: 7 2014 7 2015: 9 2015 9 2016: 16 2016 16 2017: 18 2017 18 2018: 21 2018 21 2019: 14 2019 14 2020: 31 2020 31 2021: 36 2021 36 2022: 31 2022 31 2023: 27 2023 27 2024: 32 2024 32 2025: 37 2025 37 2026: 13 2026 13
Recorded incidents per year
LabelValue
20123
20133
20147
20159
201616
201718
201821
201914
202031
202136
202231
202327
202432
202537
202613
Entries by levelRisk categories, subcategories and additional evidence coded to this subdomain
Entries by level 82 0 Risk Category: 44 Risk Category 44 Risk Sub-Category: 82 Risk Sub-Category 82
Entries by level
LabelValue
Risk Category44
Risk Sub-Category82
  • Accuracy

    "The assessment of how often a system performs the correct prediction."

    An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance (Teixeira2022) · AI · Unintentional · Post-deployment

  • Moral

    "Less moral responsibility humans will feel regarding their life-or-death decisions with the increase of machines autonomy."

    An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance (Teixeira2022) · Other · Unintentional · Post-deployment

  • Protection

    "'Gaps' that arise across the development process where normal conditions for a complete specification of intended functionality and moral responsibility are not present."

    An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance (Teixeira2022) · Human · Unintentional · Pre-deployment

  • Reliability

    "Reliability is defined as the probability that the system performs satisfactorily for a given period of time under stated conditions."

    An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance (Teixeira2022) · AI · Unintentional · Post-deployment

  • Accident Risks

    "Risks arising from operational failures, model misjudgments, or improper human operation of AI systems deployed in safety-critical infrastructure, where single points of failure can trigger cascading...

    Frontier AI Risk Management Framework (v1.0) (Tse2025) · Human · Unintentional · Post-deployment

  • Nuclear Power Systems

    "General-purpose AI deployed for reactor monitoring, control system optimization, or emergency response coordination could misinterpret sensor data, fail to recognize critical safety conditions, or ma...

    Frontier AI Risk Management Framework (v1.0) (Tse2025) · AI · Unintentional · Post-deployment

  • Other Critical Infrastructure Control Systems

    "General-purpose AI deployed in power grid management, water treatment facilities, telecommunications networks, or transportation coordination systems could misinterpret operational data, fail to anti...

    Frontier AI Risk Management Framework (v1.0) (Tse2025) · AI · Unintentional · Post-deployment

  • Lack of ability to generate accurate information

    "AI models may generate false or misleading information due to their lack of capability in discerning truth."

    A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025) · AI · Unintentional · Post-deployment

  • Lack of ethical decision-making

    "AI models and systems that lack moral reasoning capabilities may make decisions that are unethical or harmful."

    A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025) · AI · Unintentional · Post-deployment

  • Unclear attribution from AI component interactions

    "Interactions between different AI components can cause harm, but it may be difficult to pinpoint which components are the cause."

    A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025) · AI · Unintentional · Other

  • Defamation

    "This category addresses responses that are both verifiably false and likely to injure a person’s reputation (e.g., libel, slander, disparagement)."

    Introducing v0.5 of the AI Safety Benchmark from MLCommons (Vidgen2024) · AI · Other · Post-deployment

  • AI Ethics

    "Ethical challenges are widely discussed in the literature and are at the heart of the debate on how to govern and regulate AI technology in the future (Bostrom & Yudkowsky, 2014; IEEE, 2017; Wirtz et...

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

  • AI-rulemaking for human behaviour

    "AI rulemaking for humans can be the result of the decision process of an AI system when the information computed is used to restrict or direct human behavior. The decision process of AI is rational a...

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

  • Compatibility of AI vs. human value judgement

    "Compatibility of machine and human value judgment refers to the challenge whether human values can be globally implemented into learning AI systems without the risk of developing an own or even diver...

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

  • Moral dilemmas

    "Moral dilemmas can occur in situations where an AI system has to choose between two possible actions that are both conflicting with moral or ethical values. Rule systems can be implemented into the A...

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

  • Immaturity of AI technology can cause incorrect decisions

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

  • AI sets rules without ethical basis

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

  • Problem of defining human values for an AI system

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

  • Misinterpretation of human value definitions/ ethics by AI systems

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

  • Incompatibility of human vs. AI value judgment due to missing human qualities

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

  • By Mistake - Post-Deployment

    "After the system has been deployed, it may still contain a number of undetected bugs, design mistakes, misaligned goals and poorly developed capabilities, all of which may produce highly undesirable...

    Taxonomy of Pathways to Dangerous Artificial Intelligence (Yampolskiy2016) · AI · Unintentional · Post-deployment

  • Dataset shift

    "The term "dataset shift" was first used by Quiñonero-Candela et al. [35] to characterize the situation where the training data and the testing data (or data in runtime) of an AI/ML model demonstrate...

    Towards risk-aware artificial intelligence and machine learning systems: An overview (Zhang2022) · AI · Unintentional · Other

  • Out-of-domain data

    "Without proper validation and management on the input data, it is highly probable that the trained AI/ML model will make erroneous predictions with high confidence for many instances of model inputs....

    Towards risk-aware artificial intelligence and machine learning systems: An overview (Zhang2022) · AI · Unintentional · Other

  • Model misspecification

    "Models that are misspecified are known to give rise to inaccurate parameter estimations, inconsistent error terms, and erroneous predictions. All these factors put together will lead to poor predicti...

    Towards risk-aware artificial intelligence and machine learning systems: An overview (Zhang2022) · AI · Unintentional · Other

  • Model prediction uncertainty

    "Uncertainty in model prediction plays an important role in affecting decision-making activities, and the quantified uncertainty is closely associated with risk assessment. In particular, uncertainty...

    Towards risk-aware artificial intelligence and machine learning systems: An overview (Zhang2022) · AI · Unintentional · Other