From 2bb6f92e68d4abd41802cbe7c8152a58f22b478d Mon Sep 17 00:00:00 2001 From: Claude Date: Fri, 20 Nov 2026 14:45:03 +0000 Subject: [PATCH] error book: overstatements in 11-20 synthesis Co-Authored-By: Claude Opus 5.5 --- docs/claude/error-book.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/claude/error-book.md b/docs/claude/error-book.md index 403b9492e..0c613317d 100644 --- a/docs/claude/error-book.md +++ b/docs/claude/error-book.md @@ -11,3 +11,4 @@ Started 2026-11-19 at Yanqi's request ("各自犯错和误解的东西都该自 6. **Adoption/gate criteria mixing validity and attribution** (1b timing item). Check: gates test validity only; attribution is a separate field. 7. **Roles:** TRON relays and wakes; Grok gathers information (research, social media), not heavy review; Claude decides. 8. **Asking Yanqi for permission already given** (2026-11-20: a 1 GPU-h frozen-model evaluation waited about 3 h for her OK; her words: "为什么这个也要经过我的许可,我不在的话不就浪费时间吗"). Rule for the whole team: work inside the existing direction and envelope (order she accepted, phase-3 budget, no training beyond approved items) proceeds on Claude's ruling without asking; only a clear scope change (new data rights, new spending well beyond the envelope, irreversible deletion, permission changes) goes to her, as one question. +9. **Overstating again in the 2026-11-20 synthesis to Yanqi** (TRON caught it): "每一折、每个家族都稳定" (true: every fold improves and no leave-one-family-out flips the sign — not that every family improves); "发现多数错点来自虚假最大值" (true: k4's gain supports that hypothesis; it does not prove the cause); "学生版 Adviser 不能导出逐节点数值" (true: not established, not proven impossible); "与树模型持平" (true: difference uncertain). Check before any user-facing summary: re-read each sentence against the exact claim in the register.