Our apply model applies the change suggested by the chat and selected code block to the current file. We're working on extending the context window to handle 2000-3000 line files. Then, further improving accuracy and speed.
@cursor_ai
-
Faster AI Code Analysis Model Outperforms GPT-4
By
–
We've deployed a much faster apply model for files under 400 lines.
— Cursor (@cursor_ai) 14 mai 2024
It beats GPT4 and GPT4-o for short files on internal evals (but lags behind Opus).
(top is newer model, bottom is old) pic.twitter.com/wGL86PdgujWe've deployed a much faster apply model for files under 400 lines. It beats GPT4 and GPT4-o for short files on internal evals (but lags behind Opus). (top is newer model, bottom is old)
-
GPT-4o Released: 4x Faster Than GPT-4 Model
By
–
To enable, reload the editor and select GPT-4o from the model dropdown. The model appears almost 4x faster than GPT-4 in our first tests. We're still evaluating its intelligence.
-
GPT-4o Now Available in Cursor IDE
By
–
GPT-4o is available now in Cursor
— Cursor (@cursor_ai) 13 mai 2024
Enjoy! pic.twitter.com/qDp2UC3hqRGPT-4o is available now in Cursor Enjoy!
-
Cursor Copilot++ Gets 40% Speed Boost and Enhanced Capabilities
By
–
We rolled out a major performance upgrade to Cursor's Copilot++ today! The same model ~40% faster now overall, and the performance is especially improved on small edits. Next up for Copilot++: more intelligence, more capabilities, and even more context.
-
Calculate New Range Position After Text Deletion
By
–
prompt: “`
I have a selected range in my original file (selectedRange) for the file string fileContents. Then, I delete a different range deletedRange and replace it with replacementText. Please write a function to determine the new location of selectedRange. Can you do this -
Cursor Introduces GPT-4-Turbo with Enhanced Reasoning Capabilities
By
–
Cursor users can now use the new gpt-4-turbo model. We’ve observed improved reasoning on complex tasks. Example comparison between gpt-4-1106 and the new gpt-4-turbo below:
-
Copilot++ Achieves 2x Speed Improvement with Model Optimization
By
–
Copilot++ is now ~2x faster!
— Cursor (@cursor_ai) 28 mars 2024
This speedup comes from inference optimizations + our best model yet. We really like it and hope you do too ☺️ pic.twitter.com/xcp0b550GrCopilot++ is now ~2x faster! This speedup comes from inference optimizations + our best model yet. We really like it and hope you do too
-
Claude Opus Now Available in Cursor for Developers
By
–
You can now try out Claude Opus in Cursor The latest update ships with support for Pro and API key users. Enjoy!
-
GPT-4 vs Claude: Model Selection and Performance Comparison
By
–
To enable, head to Settings > Models. Note: GPT-4 still performs best on our internal tests, but Claude’s long context and reasoning abilities are impressive.