First time this benchmark impressed me - 10/10 I would believe a human spent hours making this. There are details a human would have done better (beak attaching to the head) but still impressive.
Let me know when AI patches this bug in the wheels on all the vehicles on the highway, AND my box fan when it's next to the light with the bad PWM dimming. Then we can resume our existential doom.
I find it interesting that you put the instruction ("animate this") in the system prompt, while the prompt just had the existing SVG and no actual instructions on what to do with it. Anthropic's consumer-facing tools generally don't let you do this, unless maybe you're particularly clever with Claude Code command line flags (you can start Claude Code with a custom system prompt).
Do you think this had a substantial effect on the output?
Sorry, yes, that's what I meant by being "clever with Claude Code command line flags", I guess it's not really that clever. But in general if you just launch Claude Code normally and use it via the interactive CLI, you can't change the system prompt, so most users probably never do it.
I couldn't help myself. Here is the game, one-shot on claude.ai, Opus 5 Extra. There could certainly be play-ability improvements made with 1 or 2 prompts, but neato for one-shot.
"Create a fun and cool game from this" - and pasted the code from above.
Not to be "that" person but it's not solved. The feet are reversed and isn't accurate bird anatomy. In real life, what people think of as bird's feet is actually their toes, and their "knee" is actually their tarsal (ankle bone), and their actual knee is almost hidden in their feathers.
The problem is it's kind of a question without a well defined answer. If it was just drawing a picture of a pelican, we can compare against real pelicans for accuracy. But what exactly is a pelican riding a bike supposed to look like? It's impossible, so liberties have to be taken somewhere.
I agree. Other reasoning traces simonw quoted in his blog post showed that the model made changes to consider realistic fork rake. I think this may also be the first case where the chain went inside the seat stays. The overall bike geometry is still comical but these bits show improvement in this model over prior ones.
On the other hand, given the absurdity of the original prompt, I should not necessarily expect realistic bike geometry.
how about trying to draw an airbus a320 in 3d space using only one brush tool that can be moved to specific x,y,z coordinates (and its color, size & hardness can be changed). i think fable 5.1 did quite a good job (reasoning high, cost $0,261): https://files.catbox.moe/umx102.png
