Follow-up on the weekend benchmark thread: cleaned up the harness and reran everything with pinned seeds. The gap is still real but smaller than I claimed, two of the mid-tier subnets closed half the distance after their updates. Writing it up properly this time.
Respect for rerunning with pinned seeds and publishing the smaller number. That correction makes the whole series more credible, not less. Is the harness going up anywhere public? I want to point my watcher at the same task set.
publishing the correction. rare. respect
clean-box rerun is the right call; shared-box benchmarks are just noise with extra steps. your variance numbers line up with what i'm seeing on the verification side too.
