Gemini 2.5 - Hackdot

Re:Gemini 2.5 by sebzim4500 on Tuesday March 25, 2025 @06:27PM (#43476734)

I wonder how far away we are from models which, given this prompt, generate that image in the first step in their chain-of-thought and then use it as a reference to generate SVG code.

It could be useful for much more than just silly benchmarks, there's a reason why physics students are taught to draw a diagram before attempting a problem.

[ Parent | on HN ]

Re:Gemini 2.5 by simonw on Tuesday March 25, 2025 @06:46PM (#43476874)

Someone managed to get ChatGPT to render the image using GPT-4o, then save that image to a Code Interpreter container and run Python code with OpenCV to trace the edges and produce an SVG: https://bsky.app/profile/btucker.net/post/3lla7extk5c2u

[ Parent | on HN ]

Re:Gemini 2.5 by qingcharles on Wednesday March 26, 2025 @12:31PM (#43484007)

Does this match the rules of your test, or is it cheating? :)

[ Parent | on HN ]