Users say Claude Opus 5 is strong for worlds and simulations but breaks coding workflows

omarsar0 · x · 2026-07-29

The thread says Claude Opus 5 is surprisingly strong at building complex worlds, animations, and simulations, but still lags behind GPT-5.6-Sol as a coding agent.

A follow-up reply is much harsher: after a few sessions, the user stopped using Opus 5 because it felt “ignorant” — it did things that were never asked for, ignored custom skills and tools, and broke existing workflows and loops. The core complaint is that the model is not plug-and-play for agentic coding even if it can be impressive in other creative tasks.

Related event: Users Report Claude Opus 5 Disrupts Coding Workflows(4 posts)→

Original post →

More from coding & agent

coding & agent channel →