[intalentive]

This explanation is intuitive: https://www.youtube.com/watch?v=zc5NTeJbk-k

My takeaway is that diffusion "samples all the tokens at once", incrementally, rather than getting locked in to a particular path, as in auto-regression, which can only look backward. The upside is global context, the downside is fixed-size output.

[orbital-decay]

That a not a good intuition to have. That backwards-looking pathfinding process is actually pretty similar in both types of models - it just works along a different coordinate, crude-to-detailed instead of start-to-end.

[intalentive]

Good point.