metrofun

No signup required ofc. Project site and docs: https://swobu.com

I have discovered few skills, but haven't used them yet:

  npx skills add https://github.com/anthropics/skills --skill canvas-design                                                            
  npx skills add https://github.com/anthropics/skills --skill frontend-design

What are you feeding models with? images, html?

F

proves you only need conviction to break smth

Each iteration produces some visual result. Which must feed the next iteration loop. I have tried 3 trivial scenarios - a) rasterize HTML and transduce into text using Visual AI model b) AI text model reads DOM c) You share it with designer, designer converts them into text instructions.

Visual AI samples and doesn't enumerate problems, bad at global consistency/invariants Raw DOM - text from DOM is low SNR proxy for visual state with Designer - slow loop

We need "React" moment, to solve imperative O(n^2) state transitions with declarative O(n) target states, and let the harness do the "diffing"

Got interested in some specific Machine Learning Topic and not sure where to start? Better start with a credible timely Survey of it.

cool