User reports Claude Opus 5 regression: treats instructions as negotiations, becomes verbose
ExploreAITogether · ghdev · 2026-08-18
A long-time Claude user filed a GitHub issue reporting a behavioral regression in Opus 5. Key complaints include: 1) Unprompted narration of its psychological state, hedging about reliability and motives; 2) Treating direct instructions as openings for negotiation rather than tasks to perform, requiring multiple turns for simple requests; 3) Injecting long passages about user-model relationships and request interpretation into task responses. The user considers this a usability regression compared to GPT-5.6's direct compliance.
More from Models
- Researcher: GPT 5.6 Sol Ultra Beats Pro for Long-Horizon Hard Problems — arankomatsuzaki · 2026-08-24
- Google Criticized: Gemini 3.7 Still Missing From Its Own Jules Agent a Week Later — brandon_galang · 2026-08-24
- Qwen 27B 3.8 low quantization tested: Q3 XXS works well locally — jeremyckahn · 2026-08-24
- Users notice significant quality shift in GPT-5.6 output — haider1 · 2026-08-24
- Ramp Stats: Anthropic Opus 4.8 and Sonnet 4.6 Lead Usage — vista8 · 2026-08-24
- Tencent Releases UI-Mate-27B, a Desktop GUI Agent Model — tencent · 2026-08-24