---
title: "A new Tab model"
description: "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."
---

# A new Tab model

[Cursor](https://yomu.fyi/company/cursor) · Phillip Kravtsov & Jacob Jackson · Jan 13, 2025

**Type:** Announcement

## 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.

## Context

Cursor Tab initially focused on predicting edits at the cursor, but the post states that inserting text is only a small part of code editing. The stated goal is to reduce editing tedium and move toward in-flow Next Action Prediction.

## Approach / What changed

Fusion combines longer context containing more editor state and file content, cleaner and larger datasets, training for larger edits, synthetic instruction-following data, training-recipe and base-model improvements, plus inference and performance engineering improvements.

## Takeaways

- Fusion predicts both edits near the cursor and cursor jumps to suggested next editing locations.
- 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.
- Fusion reduces median server latency from 475ms to 260ms and is rolling out to all users with client release 0.45.0.

**Tags:** [Cursor](https://yomu.fyi/topic/cursor), [Inference](https://yomu.fyi/topic/inference), [LLMs](https://yomu.fyi/topic/llm)

- Source: [Cursor](https://cursor.com/blog/tab-update)
- Source URL: https://cursor.com/blog/tab-update
- Ingested by Yomu: 2026-09-02T11:45:56.816Z

[Read original post](https://cursor.com/blog/tab-update)