Notes
Short diagnostic pieces on where and why classifications break in production.
-
Why "other" always wins
What happens inside the catch-all category, and why its size diagnoses the structure rather than the people tagging content.
- governance
- audit
- practice
-
When model agreement is just a prompt echo
Why high agreement across model runs or research syntheses does not prove a classification is right — and how to design a test that catches shared systematic error.
- audit
- design
- evaluation
-
Why one tree cannot answer two questions
On the single most common structural flaw in product and editorial taxonomies — gluing independent dimensions into one dropdown — and the two clean ways to fix it.
- design
- audit
- facets