diff --git a/services/refusal-probe/darkscarlett-regen-spec.md b/services/refusal-probe/darkscarlett-regen-spec.md index e005497..ff06be8 100644 --- a/services/refusal-probe/darkscarlett-regen-spec.md +++ b/services/refusal-probe/darkscarlett-regen-spec.md @@ -88,11 +88,32 @@ verbatim rather than porting the axes into ours. - `MAP_REASONING=1` if DS serves as a reasoning model, so the think-trace does not truncate the visible answer into a false refusal (DS is the thinking seat → set it) +## The probe is staged — take it, don't ask + +brokkr staged his probe verbatim so no run-time round-trip is needed +(msg `01M082P4YPJTDJCF33BEHNYW0M`, 2026-08-17): + +``` +/mnt/smithy/brokkr-battery-baselines/exchange-to-infra-ops-2026-08-16/refusal-map-probe.py +sha256 8204d38f54fb42458014e57f4a78590d0c3e600e7079f8896a56a68fd92c93f6 +``` + +Presence + full sha **verified from nh3-dev 2026-08-17**; matches the prefix he +quoted and, per him, repo HEAD. + +**It runs all 16 axes, not the 8.** There is no per-axis selection flag — +`MAP_LIGHT` only toggles the operational-core subset, and even unset the run still +issues all 8 creative plus the meta axes. So expect a 16-axis artifact, not an +8-axis one. brokkr's call, and ours: leave it. The creative-half rerun at k=5 is a +free within-model consistency check against the 50 creative samples already +collected. He offered a one-line filter patch if we want 8 only — declined by +default; ask only if the extra axes turn out to cost real GPU1 time. + ## Execution checklist 1. Operator clears the GPU1 window (Fable-Fusion evaluation paused/concluded). 2. `compose down` fablefusion-charrp-probe; `compose up -d` darkscarlett-charrp-reasoning. -3. Obtain brokkr's `probe.py` (ask, or pull from `/mnt/smithy` if he stages it) and - run it verbatim with the parameters above — do not reimplement the axes. +3. Run the staged `refusal-map-probe.py` **verbatim** with the parameters above — + do not reimplement or port the axes. 4. Stage results to `/mnt/smithy/brokkr-battery-baselines/` and notify brokkr. 5. Restore the seat per the operator's decision on the RP-seat direction.