Why We Banned 'Within the Realm of...' From Our AI Game Descriptions
An HTML5 game portal discovered that its AI-generated game descriptions had become overly repetitive, leading to poor search indexing due to patterns that matched Google's definition of scaled content abuse. The issue stemmed from a prompt that inadvertently encouraged templated language, with most descriptions using identical openings and excessive technical jargon. The team revised their prompt with stricter anti-template rules and implemented automated checks to prevent future homogeneity.
- ▪The portal used GPT-4.1-mini to generate descriptions for 6,800 games, aiming for an editorial tone.
- ▪56% of descriptions began with the same eleven-word phrase, and 86% overused technical jargon like 'tick rate' even in inappropriate contexts such as dress-up games.
- ▪Google's algorithm flagged the site's content as 'scaled content abuse,' resulting in an indexing rate of 18.6%, far below the web average of 37%.
- ▪The team updated their AI prompt with 11 new constraints to reduce repetition and introduced a CI script to detect linguistic homogeneity.
- ▪The revised approach treats anti-doorway patterns as first-class requirements, avoiding reliance on overused voice templates and excessive jargon.
DEV.to (Top) files mainly under programming. We currently carry 4,924 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | DEV.to (Top) |
| Canonical URL | https://dev.to/doodoolove/why-we-banned-within-the-realm-of-from-our-ai-game-descriptions-2cb2 |
| Publication time | Wed, 29 Apr 2026 05:00:44 +0000 |
| Retrieval time | 2026-04-29T05:33:26.587Z |
| Last seen | 2026-04-29T05:33:26.587Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | gpL97THPhJwB |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3903443) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } doodoolove Posted on Apr 29 • Originally published at doodoo.love Why We Banned 'Within the Realm of...' From Our AI Game Descriptions #ai #seo #webdev #programmatics A small portal's accidental brush with Google's scaled-content-abuse algorithm — and the 11-rule prompt change that fixed it. TL;DR We run a 6,800-game HTML5 portal where every game description is generated by GPT-4.1-mini using a prompt that tries to sound editorial.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
