221–230 of 253 posts
Any benchmark gaining some, even a little, traction before a model release date should at this point be considered tainted. Create your own, never publish it or write about it in any detail.
This is fantastic I've been casually spot-checking other animals in other vehicles, because my absolute dream situation here is to catch an AI lab that's demonstrably better at pelicans on bicycles than other combinations. Catching a lab cheating specifically on my one dumb benchmark would be really funny . Dylan's methodology here - generating 1008 SVGs across an 8x6 combination - is significantly more robust than a…
What if they’re not pelicanmaxxing, but svgmaxxxing in general? Because otherwise using a LLM to generate complex svgs is pretty niche and what I thought made this a good benchmark when it was new - generalized programming and spatial knowledge. Obviously image gen in svg format is not a particularly hard problem if tackled directly on its own.
I don't understand the truth to this point, and there's a clear difficulty in establishing structure, a thing that you don't need to actually do with raster image gen, right?
Like if you say "please give me 9 circles" you expect circles in the image and not just a bunch of pixel that are vaguely circle-like, right?
Earlier quoted context omitted.
Yes, but the original purpose of the benchmark (simonw, please correct me if I'm wrong!) was to test whether new models were good at novel problem solving. Things they haven't been trained on. So yes, getting better at generating SVGs is great news (and it seems they have been) but this particular benchmark still strikes me as largely worthless now, unless SVGs happen to be what you care about in particular when a ne…
I do have a private benchmark I use for that. I have a repository with an in-progress codebase and a very large planning document, I tell the new models to simply finish everything in the planning document, and I never push those changes. All of the recent models have essentially gotten it perfect which means that the models are all equivalently good for my level of needs.
This makes me think AI companies are using chat history to train the next model.
This is funny, I actually did a similar experiment just yesterday. Looking for evidence of the same, but with another twist: checking if the models would choose to create a pelican on a bicycle, if no specific bird or method of transportation was specified. My version of it: https://www.modelbias.ai/pelican-on-a-bicycle-test
Simple as they are, there are some really aesthetically pleasing penguins on skateboards in there, including from less capable models. (In fact, I would say the Opus series got progressively worse at it over time.)
This is fantastic I've been casually spot-checking other animals in other vehicles, because my absolute dream situation here is to catch an AI lab that's demonstrably better at pelicans on bicycles than other combinations. Catching a lab cheating specifically on my one dumb benchmark would be really funny . Dylan's methodology here - generating 1008 SVGs across an 8x6 combination - is significantly more robust than a…
And a man without religion is like a fish without a bicycle.
Huh. They're not "Pelicanmaxxing"... they're Ottermaxxing. Take a look at the GLM 5.2 and Deepseek V4 "animal on a plane" examples. In every case, the animal is standing on top of the plane, a clear misunderstanding of the concept of "animal on a plane"... with the exception of the Otter. The otters are sitting in a seat on the plane, looking out the window. That's Ethan Mollick's "Otter On A Plane Using WiFi" image…
This is fantastic I've been casually spot-checking other animals in other vehicles, because my absolute dream situation here is to catch an AI lab that's demonstrably better at pelicans on bicycles than other combinations. Catching a lab cheating specifically on my one dumb benchmark would be really funny . Dylan's methodology here - generating 1008 SVGs across an 8x6 combination - is significantly more robust than a…
What if they’re not pelicanmaxxing, but svgmaxxxing in general? Because otherwise using a LLM to generate complex svgs is pretty niche and what I thought made this a good benchmark when it was new - generalized programming and spatial knowledge. Obviously image gen in svg format is not a particularly hard problem if tackled directly on its own.
SVG has its neat SVGO tool that optimises SVG code, this is very clever but it won't spot easy wins such as when a group of elements can be mirrored, or an element re-used with a transform. Neither will it use the full smorgasbord of features. SVGO is not AI, however, it does a fab job of taking bloated files from Adobe Illustrator and getting something good to work with.
The bar for SVG is really low, mostly just paths, compressed and not human readable. SVG should be a human readable format, so 'circle radius 10' rather than two hundred points at six decimal places to draw the same circle.
You have to RTFM to do cool things with SVG and there is a lack of appreciation of the format amongst developers and designers.
Earlier quoted context omitted.
I do have a private benchmark I use for that. I have a repository with an in-progress codebase and a very large planning document, I tell the new models to simply finish everything in the planning document, and I never push those changes. All of the recent models have essentially gotten it perfect which means that the models are all equivalently good for my level of needs.
I have noticed that codebases I have used an AI on seem to perform better in future AI models than ones I have not. This makes me think AI companies are using chat history to train the next model.
It may be that AI performs better on such code.