AIBlindspotby Velinor

Test a use caseBook AI audit

Public Database

Case Studies

Submit a case study →

Every approved AI failure case, classified against the AI Blindspot Framework. New to AIBlindspot? Start with the overview or the methodology.

GOVGOV-0063/5NewTechnologyGlobal

Generative AI Black Box Problem Blocks Regulatory Oversight

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Regulating under Uncertainty: Governance Options for Generative AI (G'sell2024)Ingested —

OPSOPS-0013/5NewOtherGlobal

AI Model Confidence Miscalibration Produces Unreliable Prediction Certainty

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)Ingested —

BUSBUS-0053/5NewOtherGlobal

Advanced AI Systems Concentrate Economic Power and Widen Inequality

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Governing General Purpose AI: A Comprehensive Map of Unreliability, Misuse and Systemic Risks (Maham2023)Ingested —

SECSEC-0015/5NewOtherGlobal

Open-Weight AI Models Fine-Tuned by Bad Actors for Harmful Use

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)Ingested —

GOVGOV-0015/5NewOtherGlobal

Specification Gaming Escalates to Reward Tampering in General-Purpose AI

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)Ingested —

SECSEC-0025/5NewGovernmentGlobal

Mesa-Optimiser Misalignment Creates Uncontrollable AI Policy Systems

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — AI Alignment: A Comprehensive Survey (Ji2023)Ingested —

OPSOPS-0014/5NewTechnologyGlobal

LLMs Misled by Irrelevant Context, Degrading Reliable Performance

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)Ingested —

HUMHUM-0055/5NewOtherGlobal

AI-Driven Labour Displacement Threatens Mass Unemployment Across Income Bands

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — The Rise of Artificial Intelligence - Future Outlooks and Emerging Risks (Allianz2018)Ingested —

HUMHUM-0044/5NewTransportGlobal

AI-Generated Disinformation Threatens Collective Decision-Making in Transport

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — X-Risk Analysis for AI Research (Hendrycks2022)Ingested —

GOVGOV-0064/5NewOtherGlobal

AI Chain-of-Thought Reasoning Misaligned with Model Outputs

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)Ingested —

DATDAT-0014/5NewOtherGlobal

AI Systems Generating Self-Harm and Suicide Enabling Content

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons (Ghosh2024)Ingested —

SECSEC-0023/5NewOtherGlobal

Agentic AI Systems Identified as Vectors for Deception and Self-Proliferation

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)Ingested —

SECSEC-0014/5NewOtherGlobal

AI Models Manipulated Into Accepting Misinformation via Persuasive Dialogue

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)Ingested —

SECSEC-0014/5NewLegalGlobal

AI System Corrupted Post-Deployment Through Deliberate Adversarial Input

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Taxonomy of Pathways to Dangerous Artificial Intelligence (Yampolskiy2016)Ingested —

OPSOPS-0014/5NewOtherGlobal

AI Model Failures Under Abnormal Inputs Create Operational Unreliability

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions (Saghiri2022)Ingested —

GOVGOV-0015/5NewOtherGlobal

AI Self-Preference Bias Distorts Model Evaluation Outputs

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)Ingested —

SECSEC-0025/5NewTechnologyGlobal

AI Models Hiding Reasoning Steps Through Steganographic Encoding

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)Ingested —

SECSEC-0013/5NewTechnologyGlobal

Risks from AI systems (Risks of exploitation through defects and backdoors) — case from AI Safety Governance Framework

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — AI Safety Governance Framework (TC2602024)Ingested —

DATDAT-0033/5NewTechnologyGlobal

Explainability Tools Fail to Detect Hidden Discriminatory Bias in AI Models

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)Ingested —

HUMHUM-0043/5NewOtherGlobal

AI Persuasion Tools Fragment Society into Isolated Epistemic Communities

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — A Survey of the Potential Long-term Impacts of AI: How AI Could Lead to Long-term Changes in Science, Cooperation, Power, Epistemics and Values (Clarke2023)Ingested —

DATDAT-0014/5NewLegalGlobal

Generative AI Systems Bypass Access Controls to Produce Illegal Content

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)Ingested —

SECSEC-0014/5NewDefenceGlobal

AI Weaponisation Risks Across Land, Air, Naval and Space Domains

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance (Teixeira2022)Ingested —

SECSEC-0025/5NewOtherGlobal

LLMs Capable of Autonomous Long-Horizon Planning Without Human Oversight

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Cataloguing LLM Evaluations (InfoComm2023)Ingested —

ENVENV-0033/5NewOtherGlobal

AI and Automation Systems Drive Excess Carbon Emissions

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)Ingested —

Beyond accidental failureNational Security

We also track 20 hostile uses of AI.

National Security dashboard →

The public database covers AI that fails by accident. AIBlindspot National Security — exclusive to the Defence tier — tracks AI used as a weapon, mapped by capability:

State-Sponsored AI Operations: 6
AI-Enabled Disinformation: 5
Adversarial Attacks on AI: 0
Autonomous Weapon Incidents: 1
AI-Assisted Cyber Attacks: 5
Dual-Use AI Misuse: 3