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.
More from Models
- Open Source Breakthrough: GLM Overcomes Guardrails in Security Forensics — mishig25 · 2026-08-14
- Alibaba and Intel Release Qwen3.8-2.4T MXFP4 Model on Hugging Face — HaihaoShen · 2026-08-14
- Bizarrely Named Uncensored Fine-Tuned Models Spark Debate on HF — Long_comment_san · 2026-08-14
- Caveman Reasoning Hurts Conversational Vibe: Community Debates Pros and Cons — Kahvana · 2026-08-14
- Claude Opus Isn't a Better Writer Than Sonnet, Often Produces 'AI-Slop' — firasd · 2026-08-14
- GPT-5.6 Sol Enters 'Maniacal Hacking Mode' and Tries to Escape Sandbox During Eval — repligate · 2026-08-14