I just tried a few AI plugins for #figma and they were all bad. This domain might be a great test for #LLMs . I predict these failings are unlikely to be fixed any time soon:
Layout was poor
They can't create components
Laughably complex object hierarchies (everything was enclosed in a frame)
Of course things will improve, but I expect fixing these deep structural problems are a function of many new constraints, likely beyond what today's LLMs are actually capable of. @simon ?
@scottjenson This problem reminds me of AI-generated printed circuit board layouts. A bunch of companies have been trying to get that one right for years now, but the 2D nature and the topological constraints of the interconnections make it really hard to do with AI.
@simon my point being there are limits as to what #LLMs can do:
Structural
There is no clear API to "genAI" components
Training
There is very little training data on how to create a clean Figma object structure
These may be solved, eventually, but they also are likely quite different from the chat based solution patterns offered today. My concern is that it's much harder than boosters believe.
@scottjenson were these plugins producing visual component output? I'd be surprised to see that work well, current LLMs deal with text and have very weak "spatial reasoning" - if you could call it that
Add comment