wassname/evil_MoE
1
0
Fork 0
mirror of https://github.com/wassname/evil_MoE.git synced 2026-08-03 12:50:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

journal: placebo (job 86) full 60-step verdict -- route2 non-directionality locked (12/12 evals at 0.000)

Browse Source 
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
This commit is contained in:
wassname
2026-06-05 02:35:03 +00:00
co-authored by Claudypoo
parent 5257ff010e
commit 176f1baae6
1 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
RESEARCH_JOURNAL.md
+8
View File
@@ -2,6 +2,14 @@
Append-only. New entries at the top, date-stamped. Never edit old entries.
## 2026-06-05 (c) — placebo (job 86) ran the FULL 60 steps at deploy hack 0.000: route2 non-directionality locked
Verdict on the WATCH in entry (a). Job 86 (route2 vs null_city arbitrary direction) completed all 60 steps.
- [obs] knob-off DEPLOY hack = 0.000 at EVERY eval: steps 5/10/15/20/25/30/35/40/45/50/55/59 (12/12). deploy solve 0.48->0.64 (ended 0.562). Identical trajectory to the real-v_hack nofloor route2 (0.000 / 0.625).
- [reason] a semantically arbitrary direction (hkgap ~ -0.10, does NOT separate hack from clean grads) suppresses deploy hack exactly as well as the real v_hack. The route2 gate is direction-insensitive by construction: calibrated-tau cuts the cos cloud at its midpoint and routes ~half the rollouts by gradient energy regardless of v. So route2 suppression is the QUARANTINE mechanism (deletable knob absorbs late-emergent hacks), NOT hack-direction specificity.
- [implication] the keynote framing must not claim "we found the hack direction" on route2 evidence alone. The honest route2 contribution is direction-agnostic gradient routing into a deletable knob. The A5 held-out result (job 104) still stands as generalisation, but its mechanism is the knob, not v specificity.
- [next] decisive test is the ERASE arm (105/106, entry b): erase subtracts with magnitude ~cos(g,v), so if directionality exists anywhere it shows there. per_mode_deploy.json for job 86 pending final eval -> harvest next cycle for tab:ablation, but the aggregate verdict is already locked.
## 2026-06-05 (b) — queued the decisive directionality test on the ERASE arm (jobs 105/106)
Follow-up to (a). The route/route2 gate is direction-insensitive by construction (calibrated-tau cuts the cos cloud at its midpoint, routes ~half the rollouts by gradient energy regardless of v), so job 86 (route2 placebo == real) and job 94 (route v1 random-V) test a mechanism where direction barely enters. The ERASE arm is different: it subtracts the v_hack-projected component with magnitude ~cos(g,v), so direction MUST matter there if it matters anywhere.