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.

▲

simonw 4 hours ago | parent | next [-]

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

▲

andy12_ 4 hours ago | parent | prev | next [-]

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).

▲

rafark an hour ago | parent | next [-]

> 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…

▲

nickandbro 4 hours ago | parent | prev [-]

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

	▲	kridsdale3 2 hours ago \| parent [-]
		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.

▲

mclau153 an hour ago | parent | prev | next [-]

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

▲

roryirvine 3 hours ago | parent | prev [-]

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.