How one step works follows a recorded step (Team room calendar, step 1) from the raw screen through the DOM's list of clickable elements, the numbered boxes and the exact request, to image tokens, one forward pass per question, probabilities and the decision; boxes come from the page's DOM or a canvas app's hit regions, never a detector model. Every step of a run now shows what blink got: the box source, earlier actions and the questions word for word, with the request JSON. Data: cua/pipeline.json (build_pipeline.py, checked pixel for pixel) and refreshed step records in the dataset (5da6693d).
Rebuild every Blink screen with a consistent crisp interface
One visual system for all tabs: clean cards and controls, compact navigation, readable typography, aligned probability displays, sharp document previews and proper disclosures. Removes nested gray wrappers and closed-panel scrollbars. Responsive figures preserve methodology disclosures. Inference, APIs, weights and model readout are unchanged.
18 days ago
Computer use: the lane game is labelled turn-based
