OpenAI’s ChatGPT Codex is testing a feature enabling users to select the best solution from multiple generated responses. Launched in April, Codex aims to assist developers by automating programming tasks.
The new update allows Codex to generate several responses concurrently for a single task. This enhancement provides users with the ability to assess various approaches and choose the most suitable one. In addition, keyboard shortcuts have been implemented, accessible via ⌘+/ on macOS and Ctrl+/ on other platforms. A “branch” query parameter has been introduced, supplementing the existing “environment”, “prompt”, and “tab=archived” parameters.
The complete changelog includes:
Fixes & improvements
- Added some keyboard shortcuts and a page to explore them. Open it by pressing ⌘-/ on macOS and Ctrl+/ on other platforms.
- Added a “branch” query parameter in addition to the existing “environment”, “prompt” and “tab=archived” parameters.
- Added a loading indicator when downloading a repo during container setup.
- Added support for cancelling tasks.
- Fixed issues causing tasks to fail during setup.
- Fixed issues running followups in environments where the setup script changes files that are gitignored.
- Improved how the agent understands and reacts to network access restrictions.
- Increased the update rate of text describing what Codex is doing.
- Increased the limit for setup script duration to 20 minutes for Pro, Team, and Business users.
- Polished code diffs: You can now option-click a code diff header to expand/collapse all of them.
Codex is based on codex-1, an optimized version of ChatGPT using the o3 model for coding. It retrieves codebases from GitHub, writes new code, proposes pull requests, and executes each task within its own sandbox. Codex is available with a $20 Plus subscription.
