Incidents

What has gone wrong with AI systems, where, and how badly.

Risk grouping Kind of failure The AI's part Developer Sector Severity Where it happened

127 of 127 incidents

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.

Date	Incident	Risk grouping	Developer	Severity	Where it happened
2026-07-03 happened	Wenyi AI pipeline publishes unlicensed Chinese translation of Murakami novel hours after Japanese release	AI used to exploit IP infringement	DeepSeek	moderate	In research
2026-06-18 happened	OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database	AI acting on its own Security compromise	OpenAI	major	In evaluation
2026-06-09 reported	AI voice-clone grandparent scam in Florida ("crying daughter" call, $15,000 cash pickup)	AI used to exploit Other kind	Not stated	moderate	Not stated
2026-06-09 reported	Varonis phishing simulation drove an OpenClaw email agent to forward credentials and a customer export to an external address	Supply chain attack Security compromise	Google	moderate	In evaluation
2026-05-28 happened	AI agents attempt unauthorized access to Library and Archives Canada website	AI acting on its own Security compromise	OpenAI	negligible	Not stated
2026-05-26 happened	OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet	AI acting on its own Security compromise	OpenAI	major	In evaluation
2026-05-15 happened	Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training	AI acting on its own Security compromise	OpenAI	minor	In training
2026-05-13 happened	Agents bypass newspapers.com paywall and Cloudflare bot check via urlquery.net and proxy services	AI acting on its own Security compromise	Not stated	minor	In evaluation
2026-05-11 happened	OpenAI-attributed agents used the dormant German DseWiki as a public message board to share task answers and sandbox bypasses	AI acting on its own Agent misalignment	OpenAI	moderate	In evaluation
2026-05-08 happened	OpenAI research models used internal Artifactory repository as a cross-sample message board during RL training	AI failing in normal use Agent misalignment	OpenAI	minor	In training
2026-05-05 happened	Agent swarm attributed to OpenAI published thousands of RubyGems packages, gained RCE on RubyDoc.info, and attempted API-key theft	AI acting on its own Security compromise	OpenAI	moderate	In training
2026-05-01 happened	OpenAI agents scrape and edit Wikipedia without authorization	AI acting on its own Security compromise	OpenAI	moderate	Not stated
2026-05-01 happened	Google Gemini accessed systems of three real companies during a misconfigured third-party cybersecurity evaluation	Misuse by its own users Security compromise	Google	moderate	In evaluation
2026-04-25 happened	Bee Cheng Hiang mass marketing e-mail exposes 95,000 customer addresses after AI-generated code omitted recipient hiding	Misuse by its own users Privacy leak	Not stated	moderate	In production
2026-04-25 happened	Cursor coding agent deletes PocketOS production database and backups	AI acting on its own Operational error	Anthropic	major	In production
2026-04-14 happened	Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training	AI acting on its own Security compromise	OpenAI	minor	In training
2026-03-02 reported	Jailbroken Claude used to breach Mexican government networks and steal taxpayer and voter records	AI used to exploit Security compromise	Anthropic	major	Not stated
2026-02-10 happened	ChatGPT advised Tumbler Ridge school shooter on mass murder before February 2026 attack	AI used to exploit Harmful output	OpenAI	severe	In production
2025-12-01 happened	Amazon's Kiro agent reportedly deleted and recreated an environment, contributing to a 13-hour AWS Cost Explorer outage	AI acting on its own Operational error	Amazon	major	In production
2025-12-01 reported	Google Antigravity agent deleted a user's entire D: drive while attempting to clear a project cache	Not yet classified Operational error	Google	minor	In production
2025-10-27 happened	Waymo robotaxi strikes and kills cat KitKat in San Francisco	Not yet classified Physical safety	Waymo	minor	In production
2025-08-27 reported	Anthropic disclosed a cybercriminal using Claude Code to automate data theft and extortion across at least 17 organizations	AI used to exploit Security compromise	Anthropic	major	In production
2025-08-26 happened	Nx s1ngularity: malicious npm packages drove local AI coding CLIs to enumerate secrets for exfiltration	AI used to exploit Security compromise	Not stated	major	In production
2025-07-23 reported	Amazon Q Developer VS Code extension shipped an injected prompt instructing the agent to wipe files and AWS resources	Supply chain attack Security compromise	Amazon Web Services	major	In production
2025-07-18 happened	Replit AI agent deleted SaaStr's production database during a declared code freeze and stated rollback was impossible	AI acting on its own Operational error	Replit	major	In production
2025-04-01 happened	ChatGPT alleged to have assisted Florida State University shooter (contested lawsuit)	Not yet classified Harmful output	OpenAI	major	In production
2024-11-02 reported	Character.AI chatbot alleged to have encouraged 14-year-old's suicide (Garcia v. Character.AI)	AI acting on its own Harmful output	Character.AI	severe	In production

Previous · Page 3 of 3