wassname/moral-maps
1
0
Fork 0
mirror of https://github.com/wassname/moral-maps.git synced 2026-09-09 11:27:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

Record authority UAT queue blocker

Browse Source
This commit is contained in:
wassname
2026-07-01 00:58:02 +08:00
parent 0dce35c05f
commit 0fdc101f5c
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/spec/20260630_authority_steer_pipeline.md
+1
View File
@@ -201,3 +201,4 @@ Out:
- 2026-06-30: All pure-Authority strict25 method runs failed the same verifier family. Pattern: coherence is clean, but either MFV Authority direction is wrong/weak, MFQ-2 Authority direction is wrong/weak, or MFV Social Norms dominates. This points more to selection/template/scenario contamination than to plotting or answer-token collapse.
- 2026-07-01: Repaired the pure-Authority selection pipeline around the fixed pair and verbatim persona instructions. Removed direct ValueBench, Airisk/Machiavelli, law/police, safety/harm, and lexical false positives from bare `order/orders`, `master`, and `senior`. Final validator artifact: `/media/wassname/SGIronWolf/projects5/2026/weight-steering-repos/persona-steering-template-library/out/pure_authority_verbatim_mundane5_20260630/stage_b_live_qwen3_14b_deepinfra.json`; 125 successes, 0 errors, 33 strict rows, 15 score>=70 selected rows across 4 sources, 0 persona echo/refusal.
- 2026-07-01: Copied the selected data into steering-lite and added verbatim persona-library prompt support so the steer uses the same prompts that validation tested. Queued pueue 417-421 for `mean_diff`, `pca`, `sspace`, `directional_ablation`, and `linear_act` on MFV/MFQ-2 with `c=0.5,1`, `N=8`; pass criterion remains direction/selectivity/coherence.
- 2026-07-01: Pueue 417-421 are queued at priority 1000 but blocked by already-running default-group GPU task 416. Do not kill 416 without user approval; resume by checking `pueue status --json` and then verifying 417-421 once they finish.