While at a cursory glance it looks as impressive as always, subtle spatial errors, and geometry that changes as it goes out of sight and comes back again hints at the fact that Google has still yet to solve the problem of deep spatial understanding.
Which considering just how pretty and detailed this whole thing looks, imo points at a fundamental issue at how these things are trained - it's as if there's no structure to its knowledge and training, like how an artist trained to draw would first try to understand simple 2d composition, then perspective, then light and shadow, mastering each concept and gradually building up a hierarchical understanding - it seems like its trying to learn everything at once.
I would rather see an AI model that I could give a floorplan of a building and it would generate an accurate flythrough on any path, even if it looked like butt.
Im not just talking out of my arse, I did work for a while in data science/engineering, and one of the big lessons people needed to be reminded of is to clean/downsample the data - a dataset consisting of a million samples could very well take 1000x as long to process as if we downsampled the whole thing to just a couple of thousand samples and we could learn the same conclusions with the fraction of expended time/effort.
I'm sure there's a similar logic in RL, that if you dump a trillion samples into the datacenter that consumes the same power as a city, what the model learns is what it could've learned with a much more curated training set and directed approaches.