tegwick 7a374d37d2 CB-WP-0004 T05: control loop — 6 points recovered, not 25-30 ...

cb-cost gains --since, so the baseline (--pin 578dcbe, 662 responses,
$135.60) and this pass (--since 578dcbe, 83 responses, $7.82) are two
disjoint windows over the same transcripts. Every verdict is on share of
pass, since the windows differ 17x in size.

Test 1 — did mechanical turns disappear? Partly. Mechanical share fell
38.2% -> 32.4%. Six points against a predicted 25-30; reported unmet, and
no target was moved in this commit.

  environment setup   11.5% -> 0.6%   (85 turns -> 1)   met, decisively
  hub + workplan      8.5%  -> 0.0%   (46 turns -> 0)   met
  text patching       10.4% -> 9.6%                     not met
  orientation         5.1%  -> 21.2%                    not met, worse

The confound is stated before any defence of the numbers: this is the
pass that built the tools, and the two categories that missed are exactly
the two whose tools were under construction. The clean test is the next
pass, and it is carried forward rather than waived.

Test 2 — did the work relocate? Not into prose. Output tokens per
response fell 896 -> 681. Output's rising share of cost is a shrinking
denominator, not more writing. Cost per response halved and the evidence
refuses to claim it: that is compaction (mean context 232,982 ->
117,822), and attributing it to tooling would repeat CB-WP-0002's
original error in a new direction.

Test 3 — did quality hold? Yes, recorded as explicit judgment. make all
green with two gates that did not exist before, and four findings
surfaced this pass, three caught by controls written this pass — one of
them a 5.2x attribution error that would have reached the hub as a
measured number.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

2026-07-31 10:27:09 +02:00

36 KiB

Raw History

View raw