Now that I've spent ten hours with Claude Code after a few months with Codex CLI, I can say with confidence:

* Claude is much much faster
* Claude makes much stupider mistakes much more often, even with Opus 4.5
* With either agent, I end each session frustrated and exhausted

Justin Searls

After ten hours using Claude Code and comparing it to Codex CLI, Claude proves significantly faster but makes more frequent mistakes even with Opus 4.5. Both AI coding agents leave the user feeling frustrated and exhausted after sessions, highlighting current limitations in AI-assisted development tools.

Now that I've spent ten hours with…