AI research and development: AI incidents

All incidents

Developer All (1)OpenAI (1)Model All (1)Kind of failure All (1)Security compromise (1)Severity All (1)major (1) Clear filters

More filters

Risk grouping All (1)Not yet classified (1)The AI's part All (1)Agent or product All (1)Tools it had All (1)How much it acted alone All (1)Acted alone, unwatched (1)Sector All (694)Information (34)Finance and Insurance (11)automotive (7)education (6)Public Administration (6)social media (6)law enforcement (5)government (4)legal services (4)Software Publishers (4)artificial intelligence (3)Educational Services (3)healthcare (3)Retail Trade (3)software development (3)banking (2)higher education (2)legal (2)news publishing (2)retail (2)Retail (2)robotics (2)software-as-a-service (2)Technology (2)transportation (2)Transportation and Warehousing (2)AI app-building software development platform (1)AI developer tools (1)AI model development / evaluation (1)AI platform / intermediary services (1)AI research and development (1)AI safety evaluation (government research) (1)AI safety research (1)anime streaming (1)Artificial intelligence research and development (1)Arts, Entertainment, and Recreation (1)Autonomous ride-hailing (robotaxi) (1)Autonomous vehicle / robotaxi transportation (1)autonomous vehicles (1)blockchain analysis / financial technology (1)Cloud computing (1)consulting (1)Consumer hardware / smartphone manufacturing (1)critical infrastructure and e-commerce (1)CRM software (1)cryptocurrency (1)Cybersecurity (1)decentralized finance (lending protocol) (1)Defense contracting (1)direct-to-consumer toilet paper deliveries (1)Emergency call centers (911 dispatch) (1)financial services (1)Fitness and recreational sports centers (1)Food Manufacturing (1)Government AI safety and security evaluation (1)government AI safety evaluation (1)Government and electric power (1)government contracting and immigration enforcement (1)Grocery retail (1)grocery retail (1)hardware wallet manufacturing (1)Health Care and Social Assistance (1)Healthcare (1)Healthcare and government (1)Industrial automation, electronics manufacturing, semiconductors, pharmaceuticals, shipping, tire manufacturing, petrochemicals, and data center services (1)Information (software publishing / AI services) (1)Information Security research (1)Insurance (1)IT services (managed service providers) (1)Legal services (1)live events ticketing (1)matrimonial services (1)Messaging and social media platform (1)military (1)news media (1)online gambling (1)online retail (1)Open knowledge platform / nonprofit encyclopedia (1)open source software (1)photography (1)Policing (1)political campaigns (1)professional services (1)Professional, Scientific, and Technical Services (1)public administration (1)Public administration (1)Public administration and courts (1)Public administration and government (1)railway (1)real estate (1)Real estate (hobbyist manufacturing) (1)religious organisation (1)Research and development in AI safety (1)Retail Trade; Transportation and Warehousing; Finance and Insurance (1)ride-hailing (1)Ride-hailing and autonomous vehicle passenger transport (1)Scientific research and light source user facility (1)short-video platform (1)Software / AI coding tools (1)Software development (AI vibe-coding platform) (1)Software development / coding tools (1)Software development / information sector (1)Software development tools (1)Software publishing / npm ecosystem (1)Taxi and Limousine Service (1)technology (1)theme parks (1)travel (1)Where it happened All (1)In evaluation (1)

1 of 694 incidents, all dates

How this is counted

Counted by the date each incident was first reported. The bar that holds today is marked to date and is not compared. Every bar and number opens the incidents it counts.

Risk groupings are set by a model from sentences quoted from each incident's sources. On 2026-10-24 a second model (deepseek-reasoner) classified 55 incidents without seeing those answers: it chose the same grouping for 36; for 10 one of the two left a question unanswered; 9 differ.

Browse incidents by

Risk grouping: Not yet classified · AI used to exploit · AI acting on its own · AI attacked · Misuse by its own users · AI failing in normal use · Harm by design · Supply chain attack

Kind of failure: Security compromise · Harmful output · Other kind · Operational error · Agent misalignment · Hallucination · Privacy leak · Physical safety · Bias or disparate impact · IP infringement

Developer: OpenAI · Anthropic · xAI · Tesla · Google · Meta · Microsoft · Waymo · DeepSeek · Facewatch · Perplexity · Alibaba · Amazon · Amazon Web Services · Baidu · Character Technologies · Character.AI · GitHub · Peter Steinberger · Zoox · Anthropic PBC · Apple · Atlassian · Aurelian · Avride · AWS · Bondu · Butterfly Effect · Character Technologies, Inc. · Cline · Codeway · Cognitec · Context.ai · Cursor · Deloitte · DreamX · Figure AI · Flock Safety · Hugging Face · Liquid AI · Lovable · McKinsey & Company · Moltbook · Moonshot AI · Nous Research · Perplexity AI Inc. · Replit · Salesforce · Shield AI · SpaceXAI · Tencent · Trezor · TypeSafe AI · Univerads Technology Limited · Wiz · X.AI LLC · XBOW · Xiaomi · Z.AI · Z.ai (Zhipu AI) · Zoox Inc.

Model: Claude · Grok · ChatGPT · Gemini · Claude Code · GPT-4o · Mythos 5 · Codex · DeepSeek · GPT-5.6 Sol · Muse · Claude Opus 4.6 · Astra · ChatGPT Atlas · Claude Mythos 5 · Gemini 3.1 Pro · GLM-5.3 · Manus · Model Y

Agent or product: Claude Code · OpenClaw · ARTEX · Hermes Agent · ChatGPT · Codex · AI agent · Character.AI · Cursor · Gemini CLI · OpenAI agents · OpenAI Codex CLI

Tools it had: shell · browser · code_execution · email · file_read · file_write · bash · internet · network · python · internet_access · mythic · network_access · api_calls · calendar · code_generation · contacts · exploitation · file_edit · file_upload · files · Google Workspace APIs · messaging · network scanning · package_install · reconnaissance · terminal · web search

How much it acted alone: Acted alone, unwatched · Acted alone, watched by a person · A person approved each action · It suggested; a person acted

Sector: Information · Finance and Insurance · automotive · education · Public administration · social media · law enforcement · government · Legal services · Software Publishers · artificial intelligence · Educational Services · Healthcare · Retail Trade · software development · banking · higher education · legal · news publishing · Retail · robotics · software-as-a-service · technology · transportation · Transportation and Warehousing · AI app-building software development platform · AI developer tools · AI model development / evaluation · AI platform / intermediary services · AI research and development · AI safety evaluation (government research) · AI safety research · anime streaming · Artificial intelligence research and development · Arts, Entertainment, and Recreation · Autonomous ride-hailing (robotaxi) · Autonomous vehicle / robotaxi transportation · autonomous vehicles · blockchain analysis / financial technology · Cloud computing · consulting · Consumer hardware / smartphone manufacturing · critical infrastructure and e-commerce · CRM software · cryptocurrency · Cybersecurity · decentralized finance (lending protocol) · Defense contracting · direct-to-consumer toilet paper deliveries · Emergency call centers (911 dispatch) · financial services · Fitness and recreational sports centers · Food Manufacturing · Government AI safety and security evaluation · government AI safety evaluation · Government and electric power · government contracting and immigration enforcement · grocery retail · hardware wallet manufacturing · Health Care and Social Assistance · Healthcare and government · Industrial automation, electronics manufacturing, semiconductors, pharmaceuticals, shipping, tire manufacturing, petrochemicals, and data center services · Information (software publishing / AI services) · Information Security research · Insurance · IT services (managed service providers) · live events ticketing · matrimonial services · Messaging and social media platform · military · news media · online gambling · online retail · Open knowledge platform / nonprofit encyclopedia · open source software · photography · Policing · political campaigns · professional services · Professional, Scientific, and Technical Services · Public administration and courts · Public administration and government · railway · real estate · Real estate (hobbyist manufacturing) · religious organisation · Research and development in AI safety · Retail Trade; Transportation and Warehousing; Finance and Insurance · ride-hailing · Ride-hailing and autonomous vehicle passenger transport · Scientific research and light source user facility · short-video platform · Software / AI coding tools · Software development (AI vibe-coding platform) · Software development / coding tools · Software development / information sector · Software development tools · Software publishing / npm ecosystem · Taxi and Limousine Service · theme parks · travel

Severity: moderate · major · minor · severe · negligible

Where it happened: In production · In evaluation · In research · In training