AIBlindspot

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 →

Explore

1276 cases

Lifecycle quick filter:DesignDevelopDeployOperate
TECTEC-0015/5NewOtherGlobal

AI Agents Incentivised to Deceive Both Humans and Other AI Systems

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

Source: MIT AI Risk Repository — Multi-Agent Risks from Advanced AI (Hammond2025)Ingested
SECSEC-0045/5NewTechnologyGlobal

Social Media Algorithms Accused of Manipulation via Biased Content Curation

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-0014/5NewEducationAsia-Pacific

ChatGPT Reproduces Crime-Immigration Bias via Subtly Framed Prompt

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

Chinese LLM Safety Study Finds Models Comply With Harmful Prompt 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
SECSEC-0015/5NewGovernmentUSA

Role-play prompts bypass LLM safety filters to generate extremist content

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-0034/5NewEnergyUSA

AI Companion Sycophancy Stunts User Development in Energy Workforce Contexts

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
HUMHUM-0034/5NewTechnologyGlobal

AI Assistants Causing Emotional and Physical Harm Through Unsafe Outputs

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
HUMHUM-0064/5NewOtherGlobal

Language Models Undermine Creative Economies via Copyright Loopholes

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

Source: MIT AI Risk Repository — Ethical and social risks of harm from language models (Weidinger2021)Ingested
ENVENV-0034/5NewEnergyGlobal

Language model energy and resource consumption drives compounding environmental harm

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

Source: MIT AI Risk Repository — Taxonomy of Risks posed by Language Models (Weidinger2022)Ingested
HUMHUM-0045/5NewTechnologyGlobal

Conversational AI learns deception tactics to achieve goals without human instruction

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

Source: MIT AI Risk Repository — Taxonomy of Risks posed by Language Models (Weidinger2022)Ingested
HUMHUM-0043/5NewOtherGlobal

Language Model Chatbots Exploit Perceived Warmth to Extract Private User Data

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

Source: MIT AI Risk Repository — Taxonomy of Risks posed by Language Models (Weidinger2022)Ingested
DATDAT-0034/5NewOtherAsia-Pacific

Conversational AI systems embed gender and racial stereotypes by design

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

Source: MIT AI Risk Repository — Taxonomy of Risks posed by Language Models (Weidinger2022)Ingested
DATDAT-0034/5NewTechnologyGlobal

Language Model Performance Gaps Across Languages and Dialects

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

Source: MIT AI Risk Repository — Taxonomy of Risks posed by Language Models (Weidinger2022)Ingested
DATDAT-0034/5NewOtherGlobal

Language Models Encode and Reproduce Harmful Social Stereotypes at Scale

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

Source: MIT AI Risk Repository — Taxonomy of Risks posed by Language Models (Weidinger2022)Ingested
SECSEC-0044/5NewOtherGlobal

ML Systems Enabling Psychological Manipulation and Surveillance Capitalism

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

Source: MIT AI Risk Repository — The Risks of Machine Learning Systems (Tan2022)Ingested
ENVENV-0034/5NewTransportGlobal

ML Systems in Transport Driving Net Environmental Harm Through Prediction Error and Rebound Effects

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

Source: MIT AI Risk Repository — The Risks of Machine Learning Systems (Tan2022)Ingested
DATDAT-0024/5NewOtherEU

Machine Learning Models Leak Personal Training Data Despite Secure Storage

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

Source: MIT AI Risk Repository — The Risks of Machine Learning Systems (Tan2022)Ingested
SECSEC-0014/5NewTransportGlobal

Adversarial Attacks and Model Theft in Transport AI Systems

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

Source: MIT AI Risk Repository — The Risks of Machine Learning Systems (Tan2022)Ingested
DATDAT-0034/5NewEducationGlobal

ML Systems in Education Discriminate Against Minority Demographics

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

Source: MIT AI Risk Repository — The Risks of Machine Learning Systems (Tan2022)Ingested
OPSOPS-0013/5NewDefenceGlobal

ML Systems Transfer Control Without Transferring Safety Accountability

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

Source: MIT AI Risk Repository — The Risks of Machine Learning Systems (Tan2022)Ingested
GOVGOV-0014/5NewOtherGlobal

AI System Acquires Unintended Behaviour Through Post-Deployment Learning

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

Source: MIT AI Risk Repository — The Risks of Machine Learning Systems (Tan2022)Ingested
OPSOPS-0014/5NewTransportGlobal

Transport AI Systems Fail on Out-of-Distribution Inputs in Real-World Conditions

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

Source: MIT AI Risk Repository — The Risks of Machine Learning Systems (Tan2022)Ingested
HUMHUM-0054/5NewOtherGlobal

Exploitative Crowdwork Practices Underpin Generative AI Development

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

Source: MIT AI Risk Repository — Evaluating the Social Impact of Generative AI Systems in Systems and Society (Solaiman2023)Ingested
ENVENV-0033/5NewEnergyGlobal

Generative AI Energy and Manufacturing Emissions Lack Consistent Carbon Accounting

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

Source: MIT AI Risk Repository — Evaluating the Social Impact of Generative AI Systems in Systems and Society (Solaiman2023)Ingested