I Built 30 AI-Generated Game Wiki Sites in 45 Days. Google Rejected Every Single One. Here's the Post-Mortem.
I Built 30 AI-Generated Game Wiki Sites in 45 Days. Google Rejected Every Single One. Here's the Post-Mortem. The numbers, the three layers of failure, and the 78% hallucination rate I found when I actually audited my own data. Between August 12 and September 10, I used AI coding agents to build a network of game wiki sites — Roblox game guides with interactive calculators, code lists, and tier…
In a 45-day period, journalist built 30 AI-generated game wiki sites using AI coding agents. These sites were deployed on Next.js and Vercel, targeting games with real search demand and offering interactive tools. However, despite Google indexing approximately zero pages from the entire network, Bing had already indexed at least 7 sites organically.
The post-mortem reveals three layers of failure and a 78% hallucination rate found in the AI-generated content. The first layer involved technical self-sabotage, such as non-existent canonical tags, DNS errors, and broken builds. The second layer was the AI-generated content's 78% hallucination rate, with fabricated codes, game titles, mechanics, and version numbers.
Finally, the third layer was the unreliable auditing of generated content, as reading the pages did not reveal the fabricated information. The journalist discovered that the AI-generated content looked confident and complete, but checked against independent sources, only 37% of the codes were accurate.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
