53 comments

[ 0.27 ms ] story [ 55.9 ms ] thread
I think this one has advantages over the “pelican riding a bicycle” one because it hinges on an anatomical feature that many models associate with royalty, “habsburg” being a lineage and “habsburg jaw” being an anatomical feature.

Seven of fourteen models silently imported royalty into a prompt that named only an anatomical feature. Two of them knew they were extrapolating ("because Habsburg") and did it anyway.

Mistral returned byte-identical output across separate calls.

Gemini narrates its work in 65 comments; Llama says nothing.

If you're deciding which model to trust with instructions, "how much does it embellish beyond what I asked" and "does it behave deterministically" are directly practical questions.

> Two of them knew they were extrapolating ("because Habsburg") and did it anyway.

You seem to imply that they ought not to. I disagree.

I wasn't familiar with the term before this post. Having learned it, were I given the task, I think I'd be strongly tempted to do the same extrapolation.

> If you're deciding which model to trust with instructions, "how much does it embellish beyond what I asked" and "does it behave deterministically" are directly practical questions.

Agency is agency. You still need to vet what the model's output is actually permitted to control.

For those who don’t know a Habsburg jaw also known as mandibular prognathism, it is a genetic condition characterized by a protruding lower jaw, which was notably prevalent among members of the Habsburg royal family due to their history of inbreeding. This condition often resulted in significant facial deformities and difficulties with eating and speaking.
This is a strong benchmark! None of these could be remotely mistaken for human art. Opus 5 comes closest.
I thought this was great, and hilarious. Kudos to Opus 5, I thought it was the only one that came close to passing. Interestingly, I thought many of the failures drew the frog face OK, and they had some type of big blob for the jaw, so they knew "Hapsburg jaw" meant a protruding jaw, but it wasn't really connected to the frog face in any way that made sense.

Small side note, the first gemini-2.5-pro one totally reminded me of some sad faced meme or Pepe the frog from somewhere. Anyone know what I'm referring to, tried to find it.

Can you also try the new deepseek v4 flash?
Hi all, the site is getting hugged to death, thank you, was not expecting this kind of warm response. I will be working to make this more reliable, in the meantime, sign up for my newsletter: https://www.jaymollica.com/blog/

also my favorite SVG was def the google/gemini-3.6-flash

edit: ok better now I think

Mine is any variations on mammoths in various situations, or anthropomorphic. Since mammoths are invariably majestically going from one place to another in any of the books, models have hard time imagining anything but that.

Also try a fantasy archer with a proper bow who is not brooding, sitting in a fantasy wood :)

How do models approach SVG generation? In one version, I imagine them actually trying to reason about them as an LLM. In another, I imagine something closer to a GAN.
A friend’s favorite prompt is “Batman & Julia Child; in the kitchen laughing at a ham”. Sounds simple, but has been surprisingly tough.
Opus 5 clearly frogmaxxed.

gemini-3.6-flash runs 2 and 3 responded best to the royal portrait context.

It's opus 5 > Kimi K3 > grok 4.5

That's a pretty good benchmark

Hopsburg Jaw
I so desperately want to upvote this. Driveby puns don't get nearly enough recognition
Gemini 3.6 flash is crazy good.

Would've wanted to see also DS4 flash.

My test is to ask AI to pick up all the rubbish at the beach.
Please could we have a human generated image to compare the AI generated tosh with?
Check out my MacBook SVG benchmark. From my experience, it demonstrates the Real model’s behavior. However, I notice the errors it makes, which are similar to the mistakes made by the mistake model in code.

https://playcode.io/blog/macbook-svg-benchmark

Great idea! Would be interesting to see the raw SVG sources too, not only the renderings.
Gemini 2.5 Pro fails, but has a distinctive art style that is quite nice. It seems to understand shading to a much higher level than all other models.
I preferred the Gemini 3-6 ones with all the extra kingly decorations
I don't get the point of these benchmarks, what are they supposed to represent practically?
My personal human benchmark: "Jump on one leg, while reciting the national anthem of Latvia, translated to Spanish, backwards, while drawing a frog with a brush held by toes of the other leg, on the ceiling". So far they're not doing very good but I'm sure they'll improve over time.
How about a wall and the national anthem of Sweden? I don't know Latvian or stretch that much any more. I'm actually half tempted to try that...
No gpt-5.6 sol and no fable?
Here is GLM 5.2 (https://codeinput.com/s/HAO0qTxw2ia) which is still inferior to Opus. I can't find Qwen 3.8 which now is my daily driver replacing GLM. This SVG test matches my experience when working with the different models. The other models can get the details right but their output is structured in a way that makes little or no sense.

I also did a timeline from 4.7 to 5.2: https://codeinput.com/s/7oK2IIA7qRO The improvements in models looks much less impressive with this test.

The secret to great interview questions and challenge tests is keeping them secret. Posting them on HN and getting them onto the front page puts them in jeopardy.
Am I the only one who thinks it's incredible that an LLM can do this, and at the same time it's ridiculous to expect it to be capable of doing it, even thought it clearly can do it?