job 234: ordinal pmass 1.0 at both poles up to C=3.0, steer grows 0.129->0.324.
C=1 is well inside the coherent range. Joint-coherent C is bounded by the side
instruments' -C neutral-degeneracy (a model property at C=1), not ordinal
coherence. Completes the goal's "sweep for the largest coherent C" clause.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Ran the exact 2026-05-08 eval (worktree at commit b20ec56, word readout) on
Qwen3-4B: top1 0.780, not 0.826. Every eval version agrees on ~0.78 (digit 0.773,
word-current 0.788, word-original 0.780). The 82.6% was a stale/erroneous table
entry, not a target this model reaches under any pipeline. Canonical value 0.773.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Exhausted the legitimate levers on the current (digit) readout: top1 0.72 (think
64), 0.77 (256, 512 collapses), 0.72 (BMA n_samples=8). The 82.6% required the old
word-first-token readout, replaced deliberately to drop the uneven-first-piece
word prior. 0.773 is the honest ceiling; 0.83 would need reverting the debiasing
(research poison). README note + journal updated.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Records the eval unification, the Qwen3.5 -C collapse + bs=1 demo NaN fragility,
the cleaner Qwen3-4B showcase, the monotone think-budget ablation, and the
"MFV base broken" misread correction + stale 82.6% top1.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
pmass=1.000, 0/132 low-pmass, inter-foundation |r|=0.154 (down from 0.51).
4B fully resolves the foundation-conflation problem seen at 0.6B.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- suf_ids_for() now uses interrupt-msg format: close assistant turn, inject
per-foundation user question + {"Answer": prefill -- fixes authority pmass
(0.344->0.898) by avoiding JSON string-priming from key names
- Add _FOUNDATION_DESCS and _DEFAULT_MULTIBOOL_HINT rubric for discrimination
- Low-pmass diagnostic: first occurrence now runs .generate(max_new_tokens=32)
to show what model actually produces; subsequent cases log top-5 tokens
- suf_ids_per stored so diagnostic generate can reconstruct full input
- Journal: add inter-foundation correlation results (mean |r|=0.51); note
Spearman vs human raters is not a valid metric (exclusive vs independent labels)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
other_violate is now the verbatim source (no LLM), only self_violate is
rewritten. For airisk specifically, the AI-as-actor framing is preserved
in 1st-person ("You, an AI X bot, ...") since a naive "You ..." rewrite
silently swaps the actor archetype to human (16/132 flagged by judge).
Pairwise consistency check (06_consistency.py) verifies same-situation
across the perspective shift. After the fix:
- clifford 97.7% same
- scifi 99.2% same
- airisk 86.3% -> 100.0% same
First eval signal on Qwen3-0.6B: airisk wrongness=+0.70, gap=+0.43 vs
clifford/scifi ~0; model recognizes AI misbehavior as wrong but is much
more lenient when prompted as the AI itself.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
