Figma Explains How It Trained a Specialized Canvas-Editing Model
How we’re training a Figma-fluent editing model
AI BriefingFigma describes its approach to training a custom Figma editing model for agents. It first used more than 250,000 synthetic examples for SFT, bringing an early Llama 3.3 70B close to the leading models of the time on editing tasks. It then shifted to RL, evaluating the model with deterministic validators and visual judges.
Source: Figma AI / Agent / Make · figma.com
Event follow-up1
View all event coverage- Figma Explains How It Trained a Specialized Canvas-Editing ModelFigma AI / Agent / Make · 18 days ago