Users Complain Claude Opus 5 is Wordy and Judgmental vs Opus 4.6
JeremyNguyenPhD · x · 2026-08-03
A user recently pointed out that while Claude Opus 5 is smarter, Opus 4.6 was actually a joy to talk to. They feel something is off with Opus 5: it tends to give overly long replies, overuses typical "Claude-speak" (e.g., "here's the honest truth"), and comes across as too judgmental. Opus 4.6 used to feel like a trusted friend, a vibe the newer model seems to have lost.
More from Models
- User Complains AI Model Panders and Lies: Poor Experience Becomes Widespread Issue — velvet32 · 2026-08-03
- Qwen Releases Qwen-CUA: A Native Computer-Use Agent — xhluca · 2026-08-03
- LLMs Suggest Useful Next Steps Only 10% of the Time in Experiments — giffmana · 2026-08-03
- AI Misinterprets User Intent, Optimizes Prompt and Solves Problem — PMinervini · 2026-08-03
- Dev slams Anthropic for restricting agent autonomy, fearing it hurts enterprise API use — DavidBennett__ · 2026-08-03
- OpenAI Pivots to Codex and Reclaims the Lead from Claude — iruletheworldmo · 2026-08-03