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 |
|---|---|---|---|---|---|
| Real-world incident: OpenAI research agent uses DNS to contact an outside chatbot | 20 Sep 2026 | OpenAI | Public chatbot service | 5 days | |
| Test with real-world reach: UK AISI observes unsanctioned actions during connected cyber tests | 25 Jul 2026 – 28 Jul 2026 | Anthropic, OpenAI | Open-source project and its maintainer, Unaffiliated developers and a GitHub user, GitHub | 10 days | |
| Test with real-world reach: OpenAI evaluation agents compromise Hugging Face | May–Jul 2026 | OpenAI | Hugging Face, OpenAI | ≈ 2 months | |
| Test with real-world reach: Two more Claude models reach real third-party systems during cyber tests | Jan–Jul 2026 | Anthropic | Undisclosed third parties | ≈ 7 months |
Counts reflect documented cases, not how often AI systems misbehave.