A new Tab model

Summary

Cursor announces Fusion, a next-generation model for Cursor Tab, which predicts edits near the cursor and “jumps” to likely next editing locations. The post positions this as a response to the limits of cursor-only text insertion, with a broader goal of reducing code-editing tedium and moving toward in-flow Next Action Prediction. Compared with the March 2024 model, Fusion predicts over 25% more difficult edits per line, suggests over 10x longer change stretches, cuts median server latency from 475ms to 260ms, expands context from 5,500 to 13,000 tokens, and adds instant, accurate cursor jumps. These gains are attributed to cleaner and larger datasets, longer editor-state prompts, training for larger edits, synthetic instruction-following data, and inference and performance improvements. Fusion is rolling out to all users in client release 0.45.0.

Takeaways

1. 1

   Fusion predicts both edits near the cursor and cursor jumps to suggested next editing locations.

2. 2

   Against the March 2024 model, Fusion predicts over 25% more difficult edits per line, suggests over 10x longer change stretches, and expands context from 5,500 to 13,000 tokens.

3. 3

   Fusion reduces median server latency from 475ms to 260ms and is rolling out to all users with client release 0.45.0.