News for hackers. Stuff that matters.
Re:Gemini 3.5 Flash by tantalor on Tuesday May 19, 2026 @04:01PM (#48198667)
Forgetting the chainstay is typical of asking random people to draw a bicycle.

https://www.gianlucagimini.it/portfolio-item/velocipedia/

> most ended up drawing something that was pretty far off from a regular men’s bicycle

Re:Gemini 3.5 Flash by et1337 on Tuesday May 19, 2026 @04:46PM (#48199381)
Asking random people to write SVG gives even worse results
Re:Gemini 3.5 Flash by lxgr on Tuesday May 19, 2026 @05:17PM (#48199784)
Especially without being able to look at the rendered output! (At least I'd be surprised if modern server-side tool calls regularly include an SVG renderer that can show a rasterized version to the model to iterate on it.)
Re:Gemini 3.5 Flash by gpm on Tuesday May 19, 2026 @09:19PM (#48201866)
One of the many things Google was pitching today is that they're going to run things like google search with access to linux container environments to do things like run tool calls... which will presumably be able to rasterize SVGs and show them to the model.

But Simon says he runs these through the API without tool access specifically to prevent that sort of "cheating". I.e. it's an LLM benchmark not an LLM+Harness benchmark.

Re:Gemini 3.5 Flash by Eji1700 on Tuesday May 19, 2026 @06:59PM (#48200800)
Although every single render of those has pedals on the correct side as opposed to the Gemini optical illusion back pedal that tries to be both on the other side of the central gear and infront of the back wheel.

Not really a criticism but an interesting point that you would never expect a human to make that mistake even in a bad drawing.

Re:Gemini 3.5 Flash by Barbing on Wednesday May 20, 2026 @01:17AM (#48203385)
Thanks for the delightful Velocipedia