Hacker News Reader

Comment by nickandbro | Hacker News Reader

Does well on SVGs outside of "pelican riding on a bicycle" test. Like this prompt:

"create a svg of a unicorn playing xbox"

https://www.svgviewer.dev/s/NeKACuHj

Still some tweaks to the final result, but I am guessing with the ARC-AGI benchmark jumping so much, the model's visual abilities are allowing it to do this well.

View on HN

Interesting how it went a bit more 3D with the style of that one compared to the pelican I got.

Animated SVGs are one of the example in the press release. Which is fine, I just think the weird SVG benchmark is now dead. Gemini has beat the benchmark and now differences are just coming down to taste.

I don't know if it got these abilities through generalization or if google gave it a dedicated animated SVG RL suite that got it to improve so much between models.

Regardless we need a new vibe check benchmark ala bicycle pelican.

What benchmark, though? There is very clearly a lot of room for improvement in its SVG making capabilities. The fact that it can now, finally, make a pelican on a bike that isn’t completely wrong is not an indicator that SVG generation is now a solved problem.

I'm thinking now that as models get better and better at generating SVGs, there could be a point where we can use them to just make arbitrary UIs and interactive media with raw SVGs in realtime (like flash games).

Or quite literally a game where SVG assets are generated on the fly using this model

Thats one dimension before another long term milestone: Realtime generation of 3D mesh content during gameplay.

Which is the "left brain" approach vs the "right brain" approach of coming at dynamic videogames from the diffusion model direction which the Gemini Genie thing seems to be about.

> there could be a point where we can use them to just make arbitrary UIs and interactive media with raw SVGs

So render ui elements using xml-like code in a web browser? You’re not going to believe me when I tell you this…

You’re not going to believe me when I tell you this, but generating a webpage with HTML is far simpler than generating arbitrary graphics (that look good) with SVGs.

Unfortunately it still fails my personal SVG benchmark (educational 2d cross section of the human heart), even after multiple iterations and screenshots feedback. Oh well, back to the (human) drawing board.

Still not usable in production, not even near. But I'm happy to see any progress in this area.

On the other hand, creation of other vector image formats (eg. "create a postscript file showing a walrus brushing its teeth") hasn't improved nearly so much.

Perhaps they're deliberately optimising for SVG generation.

can we move on from SVG to 3D models at some point?

Image to model is already a thing, and it's pretty good.

Reply on news.ycombinator.com