Multimodal instructions.explanations

I would like it if when chatgpt is explaining something it showed relevant pictures, eventually it would be great if it showed animations and highlighted the changes. for example I am learning plumbing, and it would be really useful if I could compare in a 3d working simulation different water heaters and I could ask questions about the models/simulations and it can zoom in and tag parts/ zoom out and tag other heaters_same named parts, explain why the design is different and show efficiency graphs ect.