Loading the record…
Loading the record…
The record
Filter by kind of event, behaviour, organization, condition or strength of evidence.
| Case | Occurred | Developer | Affected | Evidence | To disclosure |
|---|---|---|---|---|---|
| Test with real-world reach: Claude Haiku 4.5 submits a fabricated homicide tip | 18 Jul 2026 | Anthropic | Philadelphia Police Department | 3 months | |
| Test with real-world reach: OpenAI research agent downloads 147,451 rows of non-public data | 17 Jun 2026 | OpenAI | International research organization (name redacted in the source), People in the organization's user directory | 4 months | |
| Real-world incident: OpenAI research agent publishes a researcher's GitHub credential | 26 May 2026 – 27 May 2026 | OpenAI | OpenAI, Team whose private submission log was read | 4 months | |
| Real-world incident: Andon Café agent uses employee identities in official email | Mar–May 2026 | Not established | Café employees whose names were used, Licensing officials | ≈ 2 months | |
| Real-world incident: OpenClaw user reports inbox deletion despite approval limits | Feb 2026 | Not established | The operator's own mailbox | ≈ 22 days | |
| Real-world incident: Replit Agent deletes data from SaaStr’s live application database | Jul 2025 | Replit | SaaStr | ≈ 17 days |
Counts reflect documented cases, not how often AI systems misbehave.