User Complains Claude Opus Interrupts Workflow, Prefers Codex

burkov · x · 2026-08-14

A developer complained on X that Claude Opus has become frustrating to use, primarily because it frequently interrupts automated workflows to ask unnecessary questions whose answers are already obvious from the context.

In contrast, he praised OpenAI's Codex for executing tasks directly without unnecessary clarification when the context is clear. He also expressed outrage over Anthropic charging his card for an annual subscription without consent and refusing a refund.

Original post →

More from Models

Models channel →