11–20 of 63 posts
The intensity of competition between models is so intense right now they are definitely benchmaxxing pelican on bike SVGs and Will Smith spaghetti dinner videos.
So, again, when the indicator becomes a target, it stops being a good indicator.
Since it’s a* FAQ… Also that pelican is pretty fly
The intensity of competition between models is so intense right now they are definitely benchmaxxing pelican on bike SVGs and Will Smith spaghetti dinner videos.
What I find interesting is that Deep Think's chain-of-thought approach helps here — you can actually watch it reason about where the pedals should be relative to the wheels, which is something that trips up models that try to emit the SVG in one shot. The deliberative process maps well to compositional visual tasks.
The intensity of competition between models is so intense right now they are definitely benchmaxxing pelican on bike SVGs and Will Smith spaghetti dinner videos.
A pelican on a bike is SFW, inclusive, yet cool.
It is not a full benchmark - rather a litmus test.
I don't think this is a good "benchmark" anymore. It's probably on everyone's training set by now.
I just asked Gemini pro to generate an SVG of an octopus dunking a basketball and it did a great job. Not even Deep Think model. Then I did "generate an svg of raccoon at a beach drinking a beer" you can go try this out yourself. Ask it to generate anything you want in SVG. use your imagination.
Rant: This is why AI is going to take over, folks are not even trying the least.
For those claiming they rigged it. Do you have any concrete evidence? What if the models have just gotten really good? I just asked Gemini pro to generate an SVG of an octopus dunking a basketball and it did a great job. Not even Deep Think model. Then I did "generate an svg of raccoon at a beach drinking a beer" you can go try this out yourself. Ask it to generate anything you want in SVG. use your imagination. Rant…
Kagi Assistant remains my main way of interacting with AI. One of its benefits is you're encouraged to try different models.
The heterogeneity in competence, particular per unit in time, is growing rapidly. If I'm extrapolating image-creation capabilities from Claude, I'm going to underestimate what Gemini can do without fuckery. Likewise, if I'm using Grok all day, Gemini and Claude will seem unbelievably competent when it comes to deep research.
The intensity of competition between models is so intense right now they are definitely benchmaxxing pelican on bike SVGs and Will Smith spaghetti dinner videos.
So, again, when the indicator becomes a target, it stops being a good indicator.
But it's still a fair target. Unless it's hard coded into Gemini 3 DT, for which we have no evidence and decent evidence against, I'd say it's still informative.