On a positive note, this is a nice look at the future and a direction that existing experiences seem likely to evolve towards.

However I did find myself wondering how crucial really were the model changes?

Imagine trying to implement these features as a wrapper around frontier apis and no 70B bespoke model.

Starting with a user query, we could ask for relevant svg diagrams, fit instruction steps or guides into layout templates, or even filter photos as the demo shows.

How much less would this simple approach leave us with?