Changelog

0.25.0-nightly

Cmd-I to Heal

Hold down cmd-I over a selection to heal the code with GPT-4. Useful for writing pseudocode and having the AI convert it into correct code. Please let us know if you find it useful!

0.25.x

Command-K Vision Support

You can now drag images into the Command-K prompt bar!

Other changes:

  • You can now search through past chats.
  • "Apply Diffs" from chat should be a bit faster.

UPDATES:

0.24.x

@Web, gpt-4-0125-preview

Using @Web in chat will give the AI the ability to crawl the web! The tools it can use include a search engine and a documentation site crawler.

This feature is still experimental. We're very interested in improving the ability of the AI to understand external libraries, and your thoughts will help us improve :).

Both pro and API key users can also try out gpt-4-0125-preview by configuring the model under Settings > OpenAI API > Configure Models. We're testing the new model right now for pro users to see if it performs better than all older versions of gpt-4. If so, will roll out as the default experience.

UPDATE (0.24.3-0.24.4): Adds ability to configure OpenAI base URL, fixes getcursor/cursor#1202.

0.23.x

New Model, Apply Button v2

  • "cursor-fast": This is a new model available in command-k and chat. Expect it to be a bit smarter than gpt-3.5, and with many fewer formatting errors.
  • Apply button: We've added some polish to the "apply codeblock" experience in chat.
  • Chat lints: If the AI suggests a code change in chat that involves a made up code symbol, we'll underline it. Availble for Python, Typescript, Rust.
  • More chat symbol links: When the chat references a code symbol, you'll often be able to click directly to it.

UPDATE (0.23.3-0.23.9): Fixes to Command-K, changelog auto-opening, editing very long lines with Copilot++, the "delete index" button, connection errors being silenced, and proxied authentication.

0.22.1-nightly

Cursor-Fast Model

Cursor-Fast is a newly trained model between gpt-3.5 and gpt-4 coding capabilities, with very fast response times (~3.5 speed). We'll be working to improve its performance over the coming weeks. Counts the same as 3.5 usage.

Try using it for Cmd+k!

Bug fixes:

  • Working WSL codebase search
  • Supports newer version of python extension
Previous
Next