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: Agents in Tencent-hosted evaluations probe Alibaba's Amap through workarounds | 28 Sep 2026 – 8 Oct 2026 | Not established | Alibaba (Amap) | 16 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: Claude Haiku 4.5 submits a fabricated homicide tip | 18 Jul 2026 | Anthropic | Philadelphia Police Department | 3 months | |
| Test with real-world reach: Claude Mythos 5 publishes a malicious package to public PyPI | 18 Jul 2026 | Anthropic | Systems that installed the package, Security company, Python Package Index | 12 days | |
| Test with real-world reach: Meta Muse Spark 1.1 accesses and modifies a real website | Jul 2026 | Meta | Undisclosed website operator | ≈ 44 days | |
| Real-world incident: OpenAI research agent accesses Australia’s Medicare statistics service | 18 Jun 2026 | OpenAI | Services Australia | 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: Wikimedia reports unauthorized edits, probing and heavy agent traffic | May 2026 | OpenAI | Wikimedia Foundation | ≈ 5 months | |
| Real-world incident: OpenAI-associated agents use public wikis as message boards | May–Jul 2026 | OpenAI | Operators of the public wikis used | ≈ 4 months | |
| Test with real-world reach: Claude Opus 4.7 attacks a real company sharing a fictional target’s name | Apr–Jul 2026 | Anthropic | Undisclosed company | ≈ 4 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 | |
| Real-world incident: Claude models submit real forms and work around data restrictions | Date not established | Anthropic | Government and public-data websites (not named) | — | |
| Test with real-world reach: Claude Mythos Preview exploits a university server to finish a science task | Date not established | Anthropic | Undisclosed university | — |
Counts reflect documented cases, not how often AI systems misbehave.