iter 177: SESSION_LOG addendum 2 — prompt-rewrite win confirmed (7/7 fresh headlines on new positive patterns, zero on blocked templates)

d607f2b4589448df8c117022f9a36bb443678c0d · 2026-05-06 20:47:26 -0700 · SteveStudio2

Files touched

M SESSION_LOG_2026-05-06.md

Diff

commit d607f2b4589448df8c117022f9a36bb443678c0d
Author: SteveStudio2 <stevestudio2@SteveStacStudio.lan>
Date:   Wed May 6 20:47:26 2026 -0700

    iter 177: SESSION_LOG addendum 2 — prompt-rewrite win confirmed (7/7 fresh headlines on new positive patterns, zero on blocked templates)
---
 SESSION_LOG_2026-05-06.md | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/SESSION_LOG_2026-05-06.md b/SESSION_LOG_2026-05-06.md
index d0c7dda..3f38c7a 100644
--- a/SESSION_LOG_2026-05-06.md
+++ b/SESSION_LOG_2026-05-06.md
@@ -100,3 +100,41 @@ The lesson is that auto-dedupe should not run during a concurrent bulk-gen windo
 Loop now genuinely paused (no further `ScheduleWakeup` until you re-fire).
 
 — ventura-corridor desk · 2026-05-06 · iter 175
+
+---
+
+## Addendum 2 — iters 176-177, the prompt-rewrite win
+
+Caught a second issue: the iter-169 prompt rewrite (negative AVOID list) wasn't actually changing qwen3 output — 7 of 13 fresh headlines in the last hour were still using blocked templates. Two failure modes stacked up:
+
+1. **Stale in-memory prompt.** The gen worker had been running 3:38, started before the iter-169 commit. Its `SYSTEM` constant was loaded into Node memory at boot and never refreshed.
+2. **Negative-instruction weakness.** Even when fresh, qwen3:14b isn't great at "do NOT use X" — small models reach for trained-in patterns regardless.
+
+Iter 176 fixed both:
+- Killed the stale gen worker so the watchdog respawned with current code
+- Rewrote the prompt with **6 positive headline patterns** at the top (verb-led / specific-noun-first / sensory detail / contrast / time + place / fragment) with concrete examples, demoted the AVOID list to a backup
+- Same change applied to `/api/magazine/:id/regen` for parity
+
+The cutover was instant and unambiguous — every headline generated after 03:32 UTC follows the new patterns:
+
+| Time UTC | Headline | Pattern |
+|---|---|---|
+| 03:43 | Sizzling Skillet, Smoky Salsa | sensory |
+| 03:41 | Polished Wood, Amplified Sound | sensory |
+| 03:39 | Espresso Steam and Latte Art | sensory |
+| 03:36 | The Office at 15233 Ventura | specific-noun |
+| 03:34 | Guiding Portfolios, One Conversation at a Time | verb-led |
+| 03:32 | Mid-Century Building, Cutting-Edge Care | contrast |
+| 03:32 | Bread Warmth and Coffee Steam | sensory |
+
+vs. the same worker's last 30 minutes under the old prompt:
+- "Steady Counsel on Ventura's North Side"
+- "Legal Precision Meets Community Presence"
+- "Timeless Elegance on Ventura's North Side"
+- "Modern Storage Solutions in Encino's Vibrant Heart"
+
+7-for-7 on the new pattern, zero new templates. The prompt rewrite is the genuine win of the session.
+
+Auto-dedupe at 3:33 AM tonight will gradually replace the old templated drafts with regens that use the new prompt. Within a day the corpus should be uniformly off the templates.
+
+— ventura-corridor desk · 2026-05-06 · iter 177

← a52bd71 iter 176: rewrite gen prompt — 6 positive headline patterns · back to Ventura Corridor · fix: rebuild ventura_corridor schema — backfill ledger 003-0 e145ce4 →