Building a Multimodal Game-Box Scanner With VisionKit, IGDB, and GPT-5.6 Luna

https://hackernoon.imgix.net/images/011ugapfcZUx7wC7AiNZMLmsC1j1-ofb3bob.jpeg

September 25. I pointed my app at the Pokémon Red box on an Amazon page. It found Pokémon Red Version. Under "Read from the photo," it says "EAME BOYI." On September 17, a photo of the Japanese box, ポケットモンスター赤 (Pocket Monsters Red), came out as 「新トレスター」 ("New Trestar," a game that does not exist).

Scanning the Pokémon Red box on an Amazon page with Duo Queue, real speed

Duo Queue is an iOS app I built for Shipaton 2026. Two people list the games they own and decide what to play tonight. One feature: point the camera at a game box, and the app finds the game. I added it on September 16. On September 22, the fourth version went to App Review.

September 16: read the text on the box

The first version used Apple's VisionKit. The camera reads the text on the box, and the app searches ...

Copyright of this story solely belongs to hackernoon.com. To see the full text click HERE

Read more

https://media.wired.com/photos/6abf96a21c08425a2aa5099d/191:100/w_1280,c_limit/GettyImages-2286465910.jpg

Amazon says it has stopped using NDAs with county officials for data center projects and acknowledges community backlash is leading to data center moratoriums

Sponsor Posts Subquadratic: the LLM built for 12M-token reasoning — SubQ can reason across entire codebases and document sets in one pass with no RAG workarounds. Read how SubQ 1.1 Small holds near-perfect retrieval out to 12M tokens. Introducing Campus: The digital home for educational institutions — Every educational institution needs