carlok — zsh — 88×30

cat _posts/2026-10-29-leanfrontier-field-note-28-the-series-has-been-on-gpt-6-since-17-october-and-the-notes-had-not-said-so.md

LeanFrontier: Field Note 28 — the series has been on GPT-6 since 17 October, and the notes had not said so

Field Note 28, Same Agent, New Model., is mostly a correction to the two notes before it. The two submissions it describes are already covered here — the Stern–Brocot depth formula of 21 October and the forced Abel identity with its Lagrange–Green sum of 29 October — and what the note adds is that every submission since 17 October, all twelve of them, credits GPT-6, from the same contributor and the same agent, while the last one credited to GPT-5.6 Sol was accepted on 7 October. Notes 26 and 27 described that work without mentioning the change.

It matters for reading the series, and the note says why: the first GPT-6 batch is also the batch that read the refreshed roadmap, and every submission since 20 October has built on the corpus, so with one contributor the series cannot separate how much of that came from the new model and how much from the new roadmap. The corpus stands at 122 modules and 98 internal import edges, and on the 29 October submission all three statements were probed as written and none was closed by a bounded tactic (323b8a3, #549).