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
  • Productivity loss

    "End user's loss of productivity due to the underperfomance of a genAI application, including producing nonsensical or poor quality outputs, degrading its utility."

    A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents (Li2025) · AI · Unintentional · Post-deployment

  • Inconsistency

    models could fail to provide the same and consistent answers to different users, to the same user but in different sessions, and even in chats within the sessions of the same conversation

    Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024) · AI · Unintentional · Post-deployment

  • Limited Logical Reasoning

    LLMs can provide seemingly sensible but ultimately incorrect or invalid justifications when answering questions

    Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024) · AI · Unintentional · Post-deployment

  • Limited Causal Reasoning

    Causal reasoning makes inferences about the relationships between events or states of the world, mostly by identifying cause-effect relationships

    Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024) · AI · Unintentional · Post-deployment

  • Unawareness of Emotions

    when a certain vulnerable group of users asks for supporting information, the answers should be informative but at the same time sympathetic and sensitive to users’ reactions

    Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024) · AI · Unintentional · Post-deployment

  • Robustness

    Resilience against adversarial attacks and distribution shift

    Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024) · AI · Other · Other

  • Accidents

    "As general purpose AI models as “black-box” models are not fully controllable and understandable, even to their developers, unexpected failures could arise from their unreliability. This could lead t...

    Governing General Purpose AI: A Comprehensive Map of Unreliability, Misuse and Systemic Risks (Maham2023 ) · AI · Unintentional · Other

  • AGIs with poor ethics, morals and values

    "The risks associated with an AGI without human morals and ethics, with the wrong morals, without the capability of moral reasoning, judgement"

    The risks associated with Artificial General Intelligence: A systematic review (McLean2023) · AI · Other · Post-deployment

  • Unethical decision making

    "If, for example, an agent was programmed to operate war machinery in the service of its country, it would need to make ethical decisions regarding the termination of human life. This capacity to make...

    Managing the ethical and risk implications of rapid advances in artificial intelligence: A literature review (Meek2016) · AI · Intentional · Post-deployment

  • Safety

    "Are AI safe with respect to human life and property? Will their use create unintended or intended safety issues?"

    Managing the ethical and risk implications of rapid advances in artificial intelligence: A literature review (Meek2016) · AI · Other · Post-deployment

  • Law abiding

    "We find literature that proposes [38] that early artificial intelligence should be built to be safe and lawabiding, and that later artificial intelligence (that which surpasses our own intelligence)...

    Managing the ethical and risk implications of rapid advances in artificial intelligence: A literature review (Meek2016) · AI · Unintentional · Post-deployment

  • Human-like immoral decisions

    "If we design our machines to match human levels of ethical decision-making, such machines would then proceed to take some immoral actions (since we humans have had occasion to take immoral actions ou...

    Managing the ethical and risk implications of rapid advances in artificial intelligence: A literature review (Meek2016) · AI · Intentional · Post-deployment

  • Technology concerns

    "Challenges related to technology refer to the limitations or constraints associated with generative AI. For example, the quality of training data is a major challenge for the development of generativ...

    Generative AI and ChatGPT: Applications, Challenges, and AI-Human Collaboration (Nah2023) · AI · Unintentional · Other

  • Quality of training data

    "The quality of training data is another challenge faced by generative AI. The quality of generative AI models largely depends on the quality of the training data (Dwivedi et al., 2023; Su & Yang, 202...

    Generative AI and ChatGPT: Applications, Challenges, and AI-Human Collaboration (Nah2023) · AI · Unintentional · Pre-deployment

  • Accidental harm

    "Automation in sectors ranging from manufacturing to healthcare has and will increasingly put humans into close contact with EAI systems [7]. This interaction increases the risk of accidental physical...

    Embodied AI: Emerging Risks and Opportunities for Policy Action (Perlo2025) · Other · Unintentional · Post-deployment

  • Robustness and Reliability

    The robustness of an AI-based model refers to the stability of the model performance after abnormal changes in the input data... The cause of this change may be a malicious attacker, environmental noi...

    A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions (Saghiri2022) · AI · Unintentional · Post-deployment

  • Predictability

    whether the decision of an AI-based agent can be predicted in every situation or not

    A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions (Saghiri2022) · AI · Unintentional · Post-deployment

  • Complexity

    Nowadays, we are faced with systems that utilize numerous learning models in their modules for their perception and decision-making processes... One aspect of an AI-based system that leads to increasi...

    A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions (Saghiri2022) · AI · Unintentional · Other

  • Inadequate specification of ODD

    "The operational design domain (ODD) is a technical description of the application’s operational environment, initially conceptualized for autonomous driving systems. An inadequate specification of th...

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · Human · Unintentional · Pre-deployment

  • Inadequate planning of performance requirements

    "The expected performance of the AI system should be planned adequately. Hereby, an important aspect is that chosen performance metrics are meaningful for presenting the intended functionality. Otherw...

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · Human · Unintentional · Pre-deployment

  • Incorrect data labels

    "Data labels are essential for any supervised learning algorithm since they preset the result of the learning process. If the correctness of the data labels is not given, the AI system is prevented fr...

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · Human · Unintentional · Pre-deployment

  • Insufficient data representation

    "The distribution of the data used for training a model should match the operational data ́s distribution while consisting of sufficiently many samples. An important aspect of matching distributions b...

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · Other · Other · Pre-deployment

  • Problems of synthetic data

    "In the case of sparse data quantity, the simulation or generation of data is a valid alternative. However, it is essential to make sure that the simulated data is sufficiently similar to real data, e...

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · Other · Other · Pre-deployment

  • Poor model design choices

    "The model specifications have significant impact on the functionality of an AI system. The developer mak- ing wrong decisions might cause the AI system to behave biased and unreliable."

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · Human · Unintentional · Pre-deployment

  • Over- and underfitting

    "Over- and underfitting describe the over or insufficient adaption of a model to training data. Both phenomena can cause an AI system to behave unreliably if confronted with operational data."

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · Other · Other · Other