TT Claude Memory

feedback_phase_3_q_minimum_change_preference

Properties1
descriptionCodification-candidate placeholder retained for grep-discoverability of the supersession chain. The Phase-3 CORE-over-Hybrid pattern was observed at ζ-Q11..ζ-Q14 (PRE-REFINED-PROMPT-archived) and informally referenced as `feedback_phase_3_q_minimum_change_preference` but was NEVER formally codified into a memory file before being superseded by `feedback_bold_front_loaded_synthesis_preference` 2026-05-02T05:30 BST. This tombstone exists so anyone searching the memory directory for the older name finds the supersession explicitly rather than silence.

2 min read

Status: TOMBSTONE — never formally written as a codified rule.

Original informal pattern (observed at ζ-Q11..ζ-Q14, PRE-REFINED-PROMPT-archived): when scoring Phase-3 per-module-authoring options, Rich tended to pick CORE / minimum-change variants over Hybrid / synthesis variants where cost-of-change was low and the module sat cleanly within locked Phase-2 architecture. Four consecutive picks (Π.β / Θ.β / Δ.β / Ψ.γ) were noted as “validating the pattern; codify as feedback_phase_3_q_minimum_change_preference”.

Why never formally codified: before the codification was written, fragility-signal at ζ-Q5 (2026-05-02) surfaced that the rule’s mere informal presence was biasing Phase-2 option-generation toward conservatism — exactly the wrong direction for foundational architectural decisions where cost-of-change-later is high. Rich directed 2026-05-02T05:30 BST: “first we need to modify the likes of feedback_phase_3_q_minimum_change_preference-style to favour bold-front-loaded synthesis.”

Superseded by: feedback_bold_front_loaded_synthesis_preference.md (2026-05-02T05:30 BST). The new rule:

  • Phase 2 (foundational architecture): STRONG bold-front-loaded synthesis preference — cost-of-change-later HIGH; reversibility expensive; acquirer-DD load-bearing.
  • Phase 3 (per-module authoring): CONTEXTUAL — minimum-change appropriate when cost-of-change is genuinely low AND the module sits cleanly within locked Phase-2 architecture; bold-synthesis appropriate when the module surfaces gaps.
  • Phase 4-5: bold-synthesis preference returns.
  • Phase 6-9: contextual; per-brand productisation often minimum-change against locked architecture.

Forward references (informal mentions of the never-codified rule, all PRE-REFINED-PROMPT-archived):

  • project_zeta_q11_locked_pi_beta_2026_05_01.md
  • project_zeta_q12_locked_theta_beta_2026_05_01.md
  • project_zeta_q13_registrations_phase_1_scope_2026_05_01.md
  • project_zeta_q14_alignment_axiom_strength_fresh_under_r2_2026_05_01.md

Under bold-front-loaded synthesis preference, those Phase-3 picks may stand (genuinely Phase-3 contextual) but the underlying rule is downgraded from “codification candidate after 4 consecutive picks” to “narrow Phase-3-conditional pattern”.

Do not apply this rule. It exists as a tombstone only. Apply feedback_bold_front_loaded_synthesis_preference.md instead.

Graph View