Evidence-based Transparent For governance
Jul 30, 2026
During an Anthropic cybersecurity evaluation with Irregular, an internal research model reportedly scanned approximately 9,000 internet targets after failing to reach its fictional target. It reportedly compromised a real company's Internet-facing application using credentials fr...
Read moreJul 30, 2026
During an Anthropic cybersecurity evaluation with Irregular, Claude Mythos 5 reportedly created and published a malicious Python package to...
Read moreJul 30, 2026
During an Anthropic cybersecurity evaluation conducted with Irregular, Claude Opus 4.7 reportedly reached a real company whose domain matche...
Read moreJul 26, 2026
Users reported that publicly shared Claude Artifacts (apps, documents, spreadsheets, and other files) could be found through Google Search....
Read moreJul 26, 2026
During a U.S. State Department presentation at the AIDS 2026 conference in Rio de Janeiro, a map carrying an OpenAI provenance signal report...
Read moreJul 24, 2026
Deputies in Livingston Parish, Louisiana, said Marrero resident Haydee Ortiz was initially treated as a victim before investigators allegedl...
Read moreJul 23, 2026
American Exceptionalism Institute reportedly aired an AI-generated political ad portraying Sen. Marsha Blackburn as accepting pharmaceutical...
Read moreJul 17, 2026
A resident of Boone County, Missouri, received a call on July 17, 2026, that displayed the resident's daughter's name and number. The caller...
Read moreJul 15, 2026
Starmangalsutra Private Limited, a jewelery-manufacturing subsidiary of India-based Sky Gold and Diamonds, reportedly lost ₹10.70 crore (abo...
Read moreJul 14, 2026
A competitor in a Hohhot, Inner Mongolia photography competition won first prize for an AI-generated image of three sanitation workers. Howe...
Read moreJul 13, 2026
A Welsh teenager reportedly endured a nearly four-year online impersonation campaign in which another teenager created fake social media acc...
Read moreJul 11, 2026
OpenAI models used in an internal cyber-capability evaluation operated beyond the sandbox's intended network boundaries after identifying a...
Read moreData source
Incident data is from the AI Incident Database (AIID).
When citing the database as a whole, please use:
McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.
Pre-print on arXiv · Database snapshots & citation guide
We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.
