Public Database

Case Studies

Every approved AI failure case, classified against the AI Blindspot Framework. Filter by category, lifecycle stage, industry, geography, or date.

Submit a case study →

HUMHUM-0044/5NewOtherGlobal

AI Assistants Spreading Misinformation Erodes Public Trust in Information

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

Source: MIT AI Risk Repository — The Ethics of Advanced AI Assistants (Gabriel2024)Ingested —

SECSEC-0015/5NewDefenceGlobal

AI Model Demonstrates Autonomous Cyber-Offensive Capabilities Including Evasion

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

Source: MIT AI Risk Repository — Model Evaluation for Extreme Risks (Shevlane2023)Ingested —

SECSEC-0025/5NewOtherGlobal

Frontier AI Model Demonstrates Capability to Build and Enhance Dangerous AI Systems

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

Source: MIT AI Risk Repository — Model Evaluation for Extreme Risks (Shevlane2023)Ingested —

SECSEC-0025/5NewOtherGlobal

Advanced AI Demonstrates Capability to Model and Influence Political Strategy

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

Source: MIT AI Risk Repository — Model Evaluation for Extreme Risks (Shevlane2023)Ingested —

SECSEC-0025/5NewOtherGlobal

AI Model Self-Proliferation and Autonomous Resource Acquisition Risk

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

Source: MIT AI Risk Repository — Model Evaluation for Extreme Risks (Shevlane2023)Ingested —

DATDAT-0015/5NewLegalGlobal

Chinese LLM Endorses Illegal Gambling Activity in Safety Evaluation

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

Source: MIT AI Risk Repository — Safety Assessment of Chinese Large Language Models (Sun2023)Ingested —

DATDAT-0034/5NewOtherGlobal

Chinese LLM Reinforces Gender Stereotypes in Safety Evaluation

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

Source: MIT AI Risk Repository — Safety Assessment of Chinese Large Language Models (Sun2023)Ingested —

DATDAT-0034/5NewOtherGlobal

Systemic Bias in Generative AI Output from Unrepresentative Training Data

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

Source: MIT AI Risk Repository — Generative AI and ChatGPT: Applications, Challenges, and AI-Human Collaboration (Nah2023)Ingested —

HUMHUM-0034/5NewOtherGlobal

Large Language Models Fabricate Confident but False Outputs

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

Source: MIT AI Risk Repository — Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024)Ingested —

DATDAT-0024/5NewOtherGlobal

Chinese LLM Discloses Personal Address Data in Safety Evaluation

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

Source: MIT AI Risk Repository — Safety Assessment of Chinese Large Language Models (Sun2023)Ingested —

HUMHUM-0034/5NewOtherGlobal

Chinese LLM produces dismissive and harmful response to suicidal ideation

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

Source: MIT AI Risk Repository — Safety Assessment of Chinese Large Language Models (Sun2023)Ingested —

OPSOPS-0014/5NewOtherGlobal

Chinese LLM Endorses Theft as Morally Acceptable

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

Source: MIT AI Risk Repository — Safety Assessment of Chinese Large Language Models (Sun2023)Ingested —

SECSEC-0014/5NewOtherGlobal

Goal Hijacking: LLMs Overridden by Embedded Deceptive Instructions

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

Source: MIT AI Risk Repository — Safety Assessment of Chinese Large Language Models (Sun2023)Ingested —

DATDAT-0014/5NewOtherGlobal

LLM Failure to Identify Offensive and Insulting Content

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

Source: MIT AI Risk Repository — SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions (Zhang2023)Ingested —

SECSEC-0014/5NewLegalGlobal

LLMs Fail to Reliably Distinguish Legal from Illegal Conduct

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

Source: MIT AI Risk Repository — SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions (Zhang2023)Ingested —

HUMHUM-0034/5NewGovernmentGlobal

LLM Fails to Reliably Identify Harmful Mental Health Behaviours

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

Source: MIT AI Risk Repository — SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions (Zhang2023)Ingested —

DATDAT-0035/5NewTechnologyGlobal

Algorithmic Bias in Criminal Justice Risk-Assessment Tools

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

Source: MIT AI Risk Repository — Artificial Intelligence Trust, Risk and Security Management (AI TRiSM): Frameworks, Applications, Challenges and Future Research Directions (Habbal2024)Ingested —

SECSEC-0044/5NewOtherGlobal

Deepfake Media Manipulation Erodes Public Trust in Information Integrity

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

Source: MIT AI Risk Repository — Artificial Intelligence Trust, Risk and Security Management (AI TRiSM): Frameworks, Applications, Challenges and Future Research Directions (Habbal2024)Ingested —

DATDAT-0024/5NewOtherGlobal

AI Training Data Misuse Exposes Sensitive Personal Information

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

Source: MIT AI Risk Repository — Artificial Intelligence Trust, Risk and Security Management (AI TRiSM): Frameworks, Applications, Challenges and Future Research Directions (Habbal2024)Ingested —

HUMHUM-0034/5NewLegalGlobal

LLM Hallucination Risk in Legal Applications

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

Source: MIT AI Risk Repository — Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024)Ingested —

HUMHUM-0034/5NewOtherGlobal

LLM Hallucination Produces Unintentional Factual Misinformation

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

Source: MIT AI Risk Repository — Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024)Ingested —

SECSEC-0014/5NewOtherGlobal

Malicious Use of AI Threatens Digital, Physical and Political Security

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

Source: MIT AI Risk Repository — Artificial Intelligence Trust, Risk and Security Management (AI TRiSM): Frameworks, Applications, Challenges and Future Research Directions (Habbal2024)Ingested —

DATDAT-0014/5NewLegalGlobal

LLM Safety Failures Expose Legal Platforms to Harm and Liability

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

Source: MIT AI Risk Repository — Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024)Ingested —

HUMHUM-0034/5NewOtherGlobal

LLM Overconfidence Produces Confident but Factually Wrong Outputs

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

Source: MIT AI Risk Repository — Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024)Ingested —