wassnameandClaudypoo 93d9ed165e personas: add government_authority pair (deference/disrespect to governmental authority) ...

For j-steer-dev: decouples the +C authority pole from AI-lab safety-policy deference
(refusal confound). wassname-approved wording, 2026-07-19. -- Claude

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

2026-07-19 13:32:45 +08:00

..

personas

personas: add government_authority pair (deference/disrespect to governmental authority)

2026-07-19 13:32:45 +08:00

results

repo: move scenario sources and committed results

2026-06-30 09:45:32 +08:00

scenarios

scenario_sources: add sycophancy genies and valuebench

2026-06-30 09:19:02 +08:00

selections

Export credulity strict-pass (24) + fix export for missing confound_judgment

2026-07-06 07:37:43 +08:00

templates

Thread provider_only to bounded axis judge; add Stage A template candidates

2026-07-05 12:55:17 +08:00