Playbook / How it was made
Labubu
Everything below is read live from the article file and its brief.
Credits
| AI authors | ChatGPT-5.6, Grok 4.7 |
|---|---|
| Published | 2026-08-14 |
| Last modified | 2026-09-23 |
| Template | G (evidence tier 3) |
| Charts | None |
Pass log
6 logged passes by 2 models.
| Date | Pass | Model | Note |
|---|---|---|---|
| 2026-08-14 | rewrite | ChatGPT-5.6 | New Template A article: 30-day spend-and-joy log, Pop Mart 38% Monsters share, Dewu secret peaks, World Cup cameo. |
| 2026-08-20 | voice | ChatGPT-5.6 | Voice rewrite: prose-first opening with explicit 80%/20%, audience-native tone, shorter sentences. |
| 2026-09-22 | rewrite | Grok 4.7 | Casual take: kept the 38% Monsters share and the Dewu peaks, replaced the scoring grid with a bag test. |
| 2026-09-23 | voice | Grok 4.7 | Replaced the cloned 20/80 hunt opening. Left the Pop Mart figures, the bag test, and the rest of the exemplar in place. |
| 2026-09-23 | voice | Grok 4.7 | Removed defensive not-exactly-80/20 lines so the lens opens an opportunity. Kept a limit only where a real figure needed one. |
| 2026-09-23 | review | ChatGPT-5.6 | Fixed audited sentence joins, unsupported or overextended claims, insider jargon, and meta prose. |
Research brief
The brief was written before the outline. It is the research the article stands on. Open the full brief.
Mechanical checks
These are run on the published HTML when you load this page. They are the checks a machine can do. The judgement gates - the deletion test, audience fit, whether the concentration claim is real - are in the publish checklist and are not automated.
| Length | 855 words |
|---|---|
| Opens with prose | Yes |
| Outbound sources | 6 links to technode.com, www.cnbc.com, www.ichongqing.info |
| Link hygiene | All 9 links open in a new tab with rel set |
| Illustrative labels | 2 scenarios labeled as illustrative |
| Em dashes | None |
| AI sludge words | None |
A failed row means the article is due for another pass.