Another user says Claude Opus 5 still feels brittle in real coding workflows
omarsar0 · x · 2026-07-29
This reply doubles down on the criticism of Claude Opus 5 as a coding agent. The user says they already know they need to adapt their workflows and skills to newer models, but this one still is not plug-and-play.
They say there is too much that it simply does wrong, and that using it feels uncomfortable. Together with the earlier comment, the thread paints Opus 5 as capable in some creative tasks but unreliable when it needs to fit into real agentic workflows.
Related event: Claude Opus 5 Criticized: Unstable as Coding Agent, Breaks Workflows(5 posts)→
More from coding & agent
- Dev builds MCP layer so Claude Code can work on servers without ever holding SSH keys — NETMESAFE · 2026-10-16
- 'Refusing to code with AI in 2026 is like refusing Google in 2005' — prasenx · 2026-10-16
- Claude Code adds idle compaction to save 1h prompt cache on idle sessions — EricBuess · 2026-10-16
- Handling agents that crash mid-task: the hard part is the unknown outcome across the network — Responsible-Dare5139 · 2026-10-16
- OpenAI DevDay Community Hackathon heads to Berlin with developer, founder and GTM tracks — paw_lean · 2026-10-16
- Data scientist career path is shifting: ML skills no longer enough, AI engineering is the new bar — mdancho84 · 2026-10-16