Source note: Local copy of a Summer Into AI 2026 submission originally published on Substack. Screenshots, video, and audio found in the post body are mirrored locally when publicly accessible; profile and avatar images are intentionally not copied. Read the canonical post.
This is another style pushing submission in a test run of different artistic styles to punk up data from data.gov. Here’s two others in the series. This post is about motor fuel, but also some fun new ideas I got to experiment with. First, can we appreciate how this system is taking arbitrary CSV datasets and turning them into something quite nice?
This experience is a lot less featured than say the bikes and scooters dataset. I was mostly inclined on this one for a particular idea: what if there were a TV that reacted to what you were doing?
So the gimmick of this experience on the data is that you have a TV set that automatically changes stations to breaking news based on what it is you’re doing. This particular data also shows some real power of something … interesting I found along the way of doing this. One can have the AI build in WhatIf simulators into your arbitrary data.
I think that’s… very, very interesting.
The image inserts really make for a dramatic intensity of the app, even if it isn’t deeply featured. But, really. It’s an app wrapping fuel data. How visually stunning should that be?
Try it here: Motor Fuel Underground
Read more here: Motor Fuel Underground - GameLab
See the other explorations:
Original source
Canonical Substack URL: https://advisoryhour.substack.com/p/summer-into-ai-eric-week3-submission-c1b.