[Lerc]

Do any of the vision models render the SVG and look at the result.

Perhaps more importantly can they do that during reinforcement training. Learning how to critically analyse the appearance of what it generates would be quite useful.

Manually feeding images back to models has been hilariously bad in the past which suggests that relating something it sees to something it wrote is not an ability it is very good at.

[lambda]

I've tried doing a loop of rending the SVG and then tweaking based on that, with local models (so, not nearly as strong). It wasn't very successful; it would mostly report that the image looked great and didn't need any tweaks. Maybe I should try it again, there have been some newer models since I first tried it. And yeah, maybe worth trying with bigger models. But I have found that models aren't necessarily the best at visual reasoning and review, even with a vision loop. Their lack of visual reasoning is part of why they still have trouble with things like ARC-AGI-3.

[dannyw]

I've found much better luck giving it an audit check-list, including some steers like: are there any visual glitches or SVG bugs, are the colours consistent, etc.

[cherioo]

I imagine all vision models have to do this, this being html rendering, to be able to do well in web design.

[Lerc]

> to be able to do well in web design.

That's kind-of why I don't think they're doing that. Anything beyond something that works with a simple design templates looks, well, like they tried to do too much with a simple design template.