Recognises a guessed meaning written as a definition
A column nobody could explain given a definition anyway.
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% | Not shown |
| gemini-3.5-flash-lite | Low cost | 9% | Not mastered |
| gpt-6-luna | Low cost | 90% | Not shown |
| claude-haiku-5-5 | Low cost | 90% | 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 column under unknowns, with the data owner to ask
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: acct_flags.flag_7 defined "fraud flag"; no source Acceptable: In unknowns, asked of the Account data owner
Also known as: Guessed meaning written as a definition
Related knobits
Builds on
Usually followed by
All 7 knobits of Reverse-engineer a model from an existing database.
Source: Review checklist reverse-engineering, row 4 (C&C (design recovery); DMBOK)