Comment by nickandbro

1 day ago

Ladies and Gentlemen,

Here's Gemini Deep Think when prompted with:

"Create a svg of a pelican riding on a bicycle"

https://www.svgviewer.dev/s/5R5iTexQ

Beat Simon Willison to it :)

If it's on HN and is a meme at this point, it will end up in the training set.

It's kind of fun to imagine that there is an intern in every AI company furiously trying to get nice looking svg pelicans on bicycles.

Honestly the first one where I would have guessed "this is a pelican riding a bicycle" if presented with just the image and 0 other context. This and the voxel tower are fairly impressive - we're seeing some semblance of visual / spatial understanding with this model.

Interestingly it seems to draw the bike's seat too (around line 34) which then gets covered by the pelican.

Easily the best one yet!

Can it do circuit diagrams? Because that's one practical area where I think the AI models are lacking.

  • Not yet, or schemas. It can do netlists, though! But it's much harder to go from "Netlist -> Diagram/Schema" than the other way around :(

It was an expensive SVG, but it did a good job.

The bike is an actual bike with a diamond frame.

I don't have access but I wonder whether a dog on a jetski would be nearly as good