flâneur

Improving Cursor Tab with online RL | Cursor - The AI Code Editor

cursor.com · 1,218 words · saved by 1 readers

At Cursor, our goal is to make developers an order of magnitude more productive. An important part of that goal is Cursor Tab, our system that predicts your next action across your codebase. Whenever you type a character or move your cursor within the editor, our Tab model tries to predict what you'll do next, and if it has sufficient confidence, we'll display its prediction as a suggestion that you can accept by pressing Tab. Our Tab model runs on every user action, handling over 400 million requests per day. As a result, we have a lot of data about which suggestions users accept and reject. This post describes how we use this data to improve Tab using online reinforcement learning. Our approach is unusual because it involves rolling out new models to users frequently throughout the day and using that data for training. Most other LLM providers train on static datasets or use paid labelers, and only roll out a new model to users as part of a named model release every few months. We tr

Blog / research At Cursor, our goal is to make developers an order of magnitude more productive. An important part of that goal is Cursor Tab, our system that predicts your next action across your codebase. Whenever you type a character or move your cursor within the editor, our Tab model tries to predict what you’ll do next, and if it has sufficient confidence, we’ll display its prediction as a suggestion that you can accept by pressing Tab. Our Tab model runs on every user action, handling over 400 million requests per day. As a result, we have a lot of data about which suggestions users acc

related reading