Figma Trained a Model That Actually Understands Figma
Figma's October 29 writeup describes how it trained its own canvas-editing model using synthetic SFT data followed by RL with designer-calibrated reward models. The results — 20% faster tasks, 60% fewer undos — are more interesting than the benchmark numbers, because undo rate is the one metric that tells you whether a model actually understood what a user meant.
Read more →