I tried that for the GPT-5 launch - a self-improving loop that renders the SVG, looks at it and tries again - and the results were surprisingly disappointing.

I should try it again with the more recent models.

I see, thanks. I guess most current models are not yet trained for this loop.

Could you please try with Opus 4.7? I think there's a chance of it doing well, considering the design/vision focus.