Improving Cursor Tab With RL | Cursor - The AI Code Editor
cursor.com · 1,218 words · saved by 4 readers
Our new Tab model makes 21% fewer suggestions while having 28% higher accept rate.
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
saved by
related reading
- Improving Cursor Tab with online RL · Cursorcursor.com
- Improving Composer through real-time RL · Cursorcursor.com
- Composer2.pdfcursor.com
- Towards self-driving codebases · Cursorcursor.com
- Scaling long-running autonomous coding · Cursorcursor.com
- More problemscursor.com
- Our problemscursor.com
- Illustrating Reinforcement Learning from Human Feedback (RLHF)huggingface.co
- Continually improving our agent harness · Cursorcursor.com
- Cursor: AI coding agentcursor.com
- Cursor: AI coding agentcursor.com
- Cursor: AI coding agentcursor.sh