VQV Signal

CREATOR TOOLS WATCH TECHNICAL

Creator reports four-day AI game build with 1,159 paintings and 140 rooms

According to a post on X by @MeticulAi, the creator gave Claude 27 reference images and a hand-written allegory of their life, with no AI used for the writing. The post says that four days later the project had made 797 calls to fal, produced 1,159 paintings using gpt-image, "NB" and Flux, and cut 212 Kling clips into sprites. These assets add up to 140 rooms across 8 worlds, and the post shows the maps. The game is described as still a work in progress, and the post had about 6 likes at the time of the snippet, after gorkem reshared it.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-11T02:45:00+00:00 Detected 2026-11-11T06:24:20+00:00
View original source

According to a post on X by @MeticulAi, the creator gave Claude 27 reference images and a hand-written allegory of their life, with no AI used for the writing. The post says that four days later the project had made 797 calls to fal, produced 1,159 paintings using gpt-image, "NB" and Flux, and cut 212 Kling clips into sprites. These assets add up to 140 rooms across 8 worlds, and the post shows the maps. The game is described as still a work in progress, and the post had about 6 likes at the time of the snippet, after gorkem reshared it.

AI-assisted summary based on the listed source.

MeticulAi says they gave Claude 27 reference images and a hand-written (no AI) allegory of their life, and four days later had 797 calls to fal, 1,159 paintings made with gpt-image, "NB" and Flux, and 212 Kling clips cut into sprites, adding up to 140 rooms across 8 worlds. The post shows the maps, and the game...

The post offers a concrete example of an AI-assisted game workflow that combines Claude with image and video tools such as gpt-image, Flux and Kling. Developers and studios testing generative asset pipelines may find the call volume and asset counts useful as a reference point. Because the game is unfinished and the signal is small, readers should wait for a playable release before judging the quality of the output.

Signal Strength 83% Technical label WATCH Public Interest 38 Category CREATOR TOOLS Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 51 Practical Impact Score 8 Novelty Interest Score 70 Consequence Score 10 Curiosity Score 32 Shareability Score 53

VQV surfaced this signal because it is recent, relevant to AI Video, connected to Scobleizer News Pulse (X).