Curious, which kind of model is used ? do y'all prefer using a lightweight model or a more capable one for code review ?

It's almost certainly Gemini but I don't know if it's Flash or Pro.

I would assume though advanced reasoning models would be best, especially since it's out of band. If I were building it maybe I'd run two adversarial models.

It actually feels smoother on my iphone, and changing liquid glass effect is huge!

Is it normal that it doesnt detect my mouth when i speak ? the sound of my voice creates random patterns. it works well for other sounds tho

I liked he idea, Would you ever consider separate ratings by model, or is dealing with model choice itself considered part of the skill?

we clearly need the mobile app

I looked in the AppStore for “symmetry draw”, and there are at least 10 such apps.