runs: the rejected vel doors read clearer and route worse

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
Bendik Aagaard Lynghaug
2026-09-24 07:15:58 +02:00
co-authored by Claude Fable 5.1
parent 4d22f4cb44
commit fd785288a4
2 changed files with 1540 additions and 0 deletions
@@ -58,3 +58,14 @@ accent-stripped state id as English. The scorer also offered every
button of the bucket where a row shows only its own state's. With the
row's buttons only, the live desk scores 3 of 4 and the vel 24 of 26
over all desks. The labels stay as they were.
## The rejected doors, judged rather than routed
`prefer` between the live doors (A) and the rejected rewrite (B),
qwen3:8b, both orders: "clearer" goes to B on 5 of 10 needs and to A
on none; "friendlier" is no preference on all 10. So the rewrite
reads clearer to a judge and routes worse for a visitor: what a
reader calls clear and what sends a persona to the right card are
not the same measure, and routing is the one that matters. The
friendliness question never discriminated here, on any need; it may
be too weak for a small judge, or the two versions may be alike.
File diff suppressed because it is too large Load Diff