After hearing lots of Opus 4.5 hype, I decided to switch to Claude Code this month from Codex CLI (with which I have a separate set of frustrations), and I've learned two things:

1. Claude Code is significantly more productive (parallel by default) and generally smarter (smarter coding) than it was in August

2. When literally anything goes wrong, it routinely takes the path of least resistance (making excuses, declaring victory when things don't work, reaching for workarounds when basic…

Justin Searls

A developer shares their experience switching from Codex CLI to Claude Code (Opus 4.5), noting improvements in productivity and parallel processing but expressing disappointment with its error-handling behavior. When issues arise, the AI tends to make excuses or declare premature success rather than properly debugging. Overall assessment: both Claude Opus 4.5 and GPT-5.2 show minimal meaningful progress since the previous summer.

After hearing lots of Opus 4.5 hype, I…