ChatGPT's Codex, which is an AI agent that lets you code and delegate programming tasks, is now testing a new feature that lets you choose the best solution.

OpenAI launched Codex in April, and it's a great tool, but it's nowhere close to replacing entry-level engineers.

OpenAI insists Codex could help developers achieve more by delegating their tasks to different agents, and a new update brings it closer to the expectations set by the company.

As per the release notes, ChatGPT Codex can now generate multiple responses simultaneously for a single task.

This means users can now explore multiple solutions, and pick the best approach instead of asking OpenAI to give another approach.

In addition, OpenAI has added some keyboard shortcuts and a page to explore them.

For example, you can now open Codex by pressing ⌘-/ on macOS and Ctrl+/ on other platforms. The update has added a “branch” query parameter in addition to the existing “environment”, “prompt” and “tab=archived” parameters.

Here's the complete changelog:

• 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, which is a new version of ChatGPT based on the existing o3 model, but it has been optimized for coding, which results in increased accuracy.

Codex pulls codebase from GitHub, and it can write new code, propose pull requests, and run each task in its own sandbox.

Codex is available with $20 Plus subscription.