Underlying data is available on GitHub: https://github.com/dylanjcastillo/blog/tree/main/_extras/pel...
Are AI labs pelicanmaxxing?
21–30 of 253 posts
Re: Are AI labs pelicanmaxxing?
#22I find it humorous that the animal + plane combo appears to be such an outlier. I assume this is due to the models assuming the user mean plain and misspelled it in the prompt.
GLM has 2 combos of "on a plane" literally sitting inside a plane, with a window and a bit of wing showing. That's funny.
Re: Are AI labs pelicanmaxxing?
#23So this is not my experience at all for asking about simple SVG icons for web-pages. Here is one of the examples I have tried for in the past, make a simple cartoon SVG knife for a map icon for a crime map.
https://x.com/CrimeDecoder/status/2080008114615537766
Can see the images for ChatGPT/Claude (Sonnet 5), and Gemini are all quite bad.
Jagged edge of LLMs. How do you explain being able to generate very complicated shapes in the Pelican example but cannot make a much simpler icon without just alluding to it is in the training data?
Re: Are AI labs pelicanmaxxing?
#24I feel like getting LLMs to spit out an SVG is akin to getting a human artist to draw something by just reciting a list of coordinates. It's insanely hard and unnatural.
Image generation models nowadays can easily generate a photorealistic pelican riding a bicycle, where the bicycle has perfect structure. But it is, of course, only a raster image.
It seems that we're missing a kind of step to decompose an image into a list of instructions (say, SVG paths, or even brush strokes with a real brush) to reproduce it properly. Doing so would probably need a true understanding of the structure of the scene, which is something that AI still struggles with to this day.
Re: Are AI labs pelicanmaxxing?
#25Having an objective score is quite difficult. Maybe it would be better to do a pairwise comparison and calculate ELO?
Just click through the models. At a glance (and highly subjective) I don't see anything jumping out as oom worse than anything else. I only noticed a model placing the animal inside a plane (with seat and small window) but other than that, they all seem similar inside each model to me.
Re: Are AI labs pelicanmaxxing?
#26join me in building the ideal training set for pelicans riding bicycles: https://github.com/scosman/pelicans_riding_bicycles
Re: Are AI labs pelicanmaxxing?
#27> All 21 pelican-bicycle images, across all seven labs, face right. No other animal/vehicle combination does that.
> However, facing right is common: 60% of all 1,008 images do it. How common depends on the animal and the vehicle, and bicycles are one of the two vehicles where it’s strongest
Of course the pelican on the bicycle is facing right. The drivetrain on a bicycle is on the right side. If you want any representation of a bicycle that shows the drivetrain you're going to show the right side of it if you want to do so without the frame occluding it. It's an excellent bet that their training data reflects this.
Citation: https://www.rei.com/c/bikes
Edited to add:
As near as I can tell, all of the bicycles are shown facing right, regardless of the direction the animal is facing (GPT 5.6-Terra, Sample 1/3). Also, in every case where the rider has legs (i.e. not the whale) both of the rider's legs are on the right side of the bicycle. This suggests a pretty serious lack of actual understanding of how a bicycle works.
Re: Are AI labs pelicanmaxxing?
#28https://playcode.io/blog/macbook-svg-benchmark I think we should stop using pelican benchmark.
I disagree with this in the blog post:
> Every single one is a pelican, on a bicycle, first try. When every student gets an A, the exam has stopped grading.
Numerous pelicans and their bikes are clearly horribly malformed. In fact none of the bike frames are correct. Fable and Opus come close, but the top of the diamond is disconnected in Fable's case and the head tube is misaligned with the front fork in Opus's case.
And of course, as the parent post shows, labs don't actually seem to be training on the pelican bike case.
Re: Are AI labs pelicanmaxxing?
#29I feel like getting LLMs to spit out an SVG is akin to getting a human artist to draw something by just reciting a list of coordinates. It's insanely hard and unnatural. Image generation models nowadays can easily generate a photorealistic pelican riding a bicycle, where the bicycle has perfect structure. But it is, of course, only a raster image. It seems that we're missing a kind of step to decompose an image into…
The pelican on a bicycle test is specifically about generating an SVG, fyi, not a raster.
Re: Are AI labs pelicanmaxxing?
#30Oh great! You've now made it a lot easier for LLMs to train on this dataset!
Your next iteration will need different animals and different transportation options. You'll run out after a few iterations.