Skip to content

v3/v4 eval: held-out validation closes measurement gaps + sycophancy negative result#24

Merged
waitdeadai merged 1 commit into
mainfrom
evaluation/hooks-v3
May 23, 2026
Merged

v3/v4 eval: held-out validation closes measurement gaps + sycophancy negative result#24
waitdeadai merged 1 commit into
mainfrom
evaluation/hooks-v3

eval(v3/v4): results docs, Spanish locale (no-sycophancy 9/9), v4 neg…

20bfa6c
Select commit
Loading
Failed to load commit list.