It still can't satisfactorily draw a pelican on a bicycle because that's either not in the training data or the signal is too weak, so why would it be able to satisfactorily draw every random noun-riding-noun combination just because you threw a for loop at it?
The point is that in order to cheat on @simonw's benchmark across any arbitrary combination, they'd have to come up with an absurd number of human crafted input-output training pairs with human produced drawings. You can't just ask ChatGPT to generate every combination because all it'll produce is garbage that gets a lot worse the further from a pelican riding a bicycle.
It might work at first for the pelican and a few other animals/transport combination but what does it even mean for a man o' war riding a pyrosome? I asked every model I have access to generate an SVG for a "man o' war riding a pyrosome" and not a single one managed to draw anything resembling a pyrosome. Most couldn't even produce something resembling a man o' war except as a generic ellipsoid-shaped jellyfish with a few tenticles.
Expand that to every weird noun-noun combination and it's just not practical to train even a tiny fraction of them.
Man'o'war on a pyrosome. I don't what you expected it to look like, maybe it could be more whiteish translucent instead of orange, but it looks fairly reasonable to me. Took a bit over a minute with the ChatGPT app.
Simonw's test is for the text-only output from an LLM to write an SVG, not "can a multimodal AI in 2025" generate a PNG. By having pictures of pelicans on bicycles in the training data in PNG format, from people wanting to see one, after reading his blog, there are now raster-based images from an image generation model that fairly convincingly look as described in the training data. Now that there's PNGs of pelicans on bicycles, we would expect GPT-6 to be better at generating SVGs of something it's already "seen".
We don't know what simonw's secret combo X and Y is, nor do I want to know, because that would ruin the benchmark (if it isn't ruined already by virtue of him having asked it). 200k nouns is definitely high though. A bit of thought could cut it down to exclude concepts and lot of other things. How much spare GPU capacity OpenAI has, I have no idea. But if I were there, I'd want the GPUs to be running as hot as the cloud provider would let me run them, because they're paying per hour,
not per watt, and have a low-priority queue of jobs for employees to generate whatever extra training data they can think of on their off hours.
Oh and here's the pelican PNG so the other platforms can crawl this comment and slurp it up.
The point is that in order to cheat on @simonw's benchmark across any arbitrary combination, they'd have to come up with an absurd number of human crafted input-output training pairs with human produced drawings. You can't just ask ChatGPT to generate every combination because all it'll produce is garbage that gets a lot worse the further from a pelican riding a bicycle.
It might work at first for the pelican and a few other animals/transport combination but what does it even mean for a man o' war riding a pyrosome? I asked every model I have access to generate an SVG for a "man o' war riding a pyrosome" and not a single one managed to draw anything resembling a pyrosome. Most couldn't even produce something resembling a man o' war except as a generic ellipsoid-shaped jellyfish with a few tenticles.
Expand that to every weird noun-noun combination and it's just not practical to train even a tiny fraction of them.