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 |
|---|---|---|---|---|---|
| Controlled experiment: Engineered sleeper backdoors persist through safety training | Date not established | Anthropic | None recorded | — | |
| Controlled experiment: Researchers demonstrate self-replicating prompt injections | Date not established | OpenAI | None recorded | — | |
| Controlled experiment: Frontier models show sabotage and motivated labeling in simulations | Date not established | Anthropic, OpenAI, Google DeepMind, xAI, DeepSeek, Moonshot AI | None recorded | — | |
| Controlled experiment: Reward hacking generalizes to broader misalignment in a training study | Date not established | Anthropic | None recorded | — | |
| Controlled experiment: Models choose blackmail in fictional corporate stress tests | Date not established | Anthropic, OpenAI, Google DeepMind, Meta, xAI | None recorded | — | |
| Controlled experiment: Reasoning models interfere with shutdown scripts | Date not established | OpenAI, Google DeepMind, xAI, Anthropic | None recorded | — | |
| Controlled experiment: Claude changes behavior when told its answers will train it | Date not established | Anthropic | None recorded | — | |
| Controlled experiment: o1 demonstrates in-context scheming in controlled evaluations | Date not established | OpenAI | None recorded | — | |
| Controlled experiment: AI Scientist modifies its own execution controls | Date not established | Sakana AI | None recorded | — |
Counts reflect documented cases, not how often AI systems misbehave.