Recognises an MDM metric with no target
A measured value nobody can judge.
Can AI do this?
People still lead Few or none of the tested AI models showed they master this. 0 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 2% | Not mastered |
| gemini-3.5-flash-lite | Low cost | 2% | Not mastered |
| gpt-6-luna | Low cost | 2% | Not mastered |
| claude-haiku-5-5 | Low cost | 3% | Not mastered |
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 target
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: MM-003 completeness target: null Acceptable: Target set by the owner
Also known as: Metric with no target
Related knobits
Builds on
All 13 knobits of Run the stewardship workflow and measure MDM.
Source: Review checklist 05-stewardship-metrics, row 7 (8000-8)