Codex vs Claude Code: The Missing Piece Is the Harness

Welcome to the forum!

eventanilha:

Claude Opus and GPT-5.4 xHigh, for me, are basically tied as models.

Thanks for sharing that perspective—it’s useful to hear comparisons like this.

Note: I am not an OpenAI employee.

While OpenAI developers may read forum discussions, they are generally more active on the OpenAI Codex GitHub repository.

If you’re exploring further, these sections are often informative:

• Recent commits — ongoing development activity
• Issues — bug reports and troubleshooting
• Enhancement requests — proposed features and improvements
• Discussions — broader conversations and ideas

These can provide additional context, updates, and opportunities to contribute or follow development more closely.

Also see:

Codex features are prioritized by votes in GitHub issues tab Codex

FYI We prioritize feature requests based on upvotes from the community. If a feature request doesn’t get enough upvotes, we’ll close it. It’s therefore important for a feature request to have a clear and compelling title and description. We also recommend that feature requests focus on the problem statement rather than a solution. Describe the use case and what problem you’d like to see solved. There are often multiple ways to address a given problem. Source Note: In GitHub feature request…