Recognises a model change released without approval
A change released with no approver.
Can AI do this?
People still lead Few or none of the tested AI models showed they master this. 1 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 90% | Mastered |
| gemini-3.5-flash-lite | Low cost | 90% | Not shown |
| gpt-6-luna | Low cost | 90% | Not shown |
| claude-haiku-5-5 | Low cost | 90% | Not shown |
Mastered means a probability of at least 90% that the model has this knobit, estimated from its graded answers. “Not shown” means the answers do not settle it either way. How the models are tested.
What it looks like in practice
Expected result: The approver the plan names
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: MC-033 approved_by: null Acceptable: The approver named in the plan
Also known as: Change not approved
Related knobits
Builds on
- K-916 Explains data model versioning and change management
- K-921 Explains data modelling and design standards
All 7 knobits of Maintain and version data models.
Source: Review checklist maintenance-versioning, row 6 (ITIL; DMBOK §6)