Thanks for not using AI to write this. So much more pleasant to read.
Are AI labs pelicanmaxxing?
111–120 of 253 posts
Re: Are AI labs pelicanmaxxing?
#112Earlier quoted context omitted.
I don't think this small amount generalization to other animals and vehicles is strong evidence they haven't trained on this, either directly or more generally.
Honest question how could they possibly train on this as there are no good SVG pelicans to train off right? So they’re just training off a bunch of bad ones which should lead to just bad pelicans, but the pelicans are getting better.
It’s not hard for a visual model to score the quality of that output though, which would be a pretty good fitness function.
Re: Are AI labs pelicanmaxxing?
#113And a whole universe of random tests got baked into the AI’s training data. Websites of antelopes driving trains and hammerhead sharks swinging in a tyre swing were created. It was a short while until AI became so focused on animals that it gave up competing with developers. Life became sane again.
Re: Are AI labs pelicanmaxxing?
#114This 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.
If they're optimizing for SVG generation, then that's an excellent outcome in my opinion. Vector images shouldn't be "pretty niche".
Re: Are AI labs pelicanmaxxing?
#115AI rating AI? Am I missing something.
I'm surprised (but not really) that you're the only comment I see even mentioning it. The ratings may be even lower quality than the SVGs.
Obviously they're all a bit cartoon-y, what else do you expect from SVGs. But I'm not convinced you could find a single human on Earth over the age of 4 who would seriously give the vehicle in GPT/1/whale/plane a 5/5.
Browse through the options a bit and the rest is not that much better. Grok/2/cat/plane, one of the more accurate planes, got a 2/5. For the most part, vehicles entirely missing do get a 1/5, except for whatever it is in Gemini/1/heron/plane scoring 4. Animals inside planes get completely random vehicle scores I guess.
The cats are all orange, except for a few of the skateboard cats that are black. I'm sure there's nothing to read into there...
Well, I've convinced myself that the next effective test of multimodal models will be whether their judgments of LLM-generated SVG airplanes are anywhere close to reasonable.
Re: Are AI labs pelicanmaxxing?
#116Earlier quoted context omitted.
Does asking for a dagger help?
If you look at the raster image ChatGPT generated, that is fine. It is just this example (and other simple SVG icons I have asked for) result in pretty bad SVGs. It just makes me highly suspicious that the LLMs are learning shape primitives and extrapolating to new shapes, vs just having a big dictionary of prior examples and stitching them together.
Don't judge the dog's technique. The miracle is that it's dancing.
Are we best to assume an LLM is a blind programmer? Any HN comments from blind programmers tasked with creating SVG icons? Only relevant comment I could find from ctoth was about accessibility: https://news.ycombinator.com/item?id=7185771
Projecting how you think onto what the LLM is doing or should be doing, is probably a mistake on your part.
I recently spent a little time trying to understand exactly why Gemini was misexplaining $X. $X = {why the generated LaTeX visually didn't match what it was asked to do}. It was enlightening.
Re: Are AI labs pelicanmaxxing?
#117I recently had the following conversation with Claude: Me: how many P's are in the following text? [Pasted text] Claude: There are 14 P's, all lowercase (no capital P's) Me: how many in "strawberry"? Claude: there are 3 R's in the word "strawberry".
I tried this with Gemini 3.6 Flash
Me:how many P's are in the following text? [Pasted text with 10 P's]
Gemini: There are 9 "P"s (1 uppercase P and 8 lowercase ps) in the provided text. [List of words except the one missed]
Me: How many in strawberry?
Gemini: Something went wrong (1096)
Re: Are AI labs pelicanmaxxing?
#118Earlier quoted context omitted.
But that's a genuine worthwhile capability. It's like benchmarkmaxxing on a weightlifting competition by getting really strong.
How useful actually is this? It generates SVGs of pelicans on bicycles, sure, and some of them are (almost) spatially correct. But, none of them look good . AI image generation suffers from this more generally. You can generate pictures of pelicans, sure. Newer models clearly generate images with more pelican-ness than before. But all of it is still uglier than sin. Drawing things accurately is one thing, making resu…
I used Claude to plan some landscaping, and it gave me SVG diagrams of flower beds showing where to place plants and their approximate mature size. It was pretty useful.
Re: Are AI labs pelicanmaxxing?
#119This 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.
Gemini have absolutely been SVGmaxxing. They've openly talked about it.
Re: Are AI labs pelicanmaxxing?
#120Earlier quoted context omitted.
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.
If they're optimizing for SVG generation, then that's an excellent outcome in my opinion. Vector images shouldn't be "pretty niche".
Please it's almost my primary bench for drafting understanding.
I'm almost about to post that xkcd 810