I don't think this small amount generalization to other animals and vehicles is strong evidence they haven't trained on this, either directly or more generally.

▲

conception 9 hours ago | parent [-]

Honest question how could they possibly train on this as there are no good SVG pelicans to train off right? So they’re just training off a bunch of bad ones which should lead to just bad pelicans, but the pelicans are getting better.

	▲	unholiness 7 hours ago \| parent \| next [-]
		Training on generating SVGs directly at all is already fairly niche. Generating full scenes with a cartoony character is even nicher. But there's plenty of non-pelican cartoony SVG content out there (created, not written, by humans with vector design tools), and more importantly, plenty of vision models to give feedback on the output (just raster as a png). You could easily hill climb this niche skill, if you cared.
	▲	alexthehurst 9 hours ago \| parent \| prev \| next [-]
		It’s not hard for a visual model to score the quality of that output though, which would be a pretty good fitness function.
	▲	raincole 6 hours ago \| parent \| prev [-]
		They can easily afford 1000 human made pelican svg files if they want. I think you underestimate how much resources SotA AI companies have. (I'm not saying that they did that. I'm just saying they can.)