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
- GLM 5.5 rumored to drop soon, coding ability expected to match frontier models — bindureddy · 2026-10-16
- Five rounds of adversarial prompting make Opus 5.5 and Argon converge on identical output — LanceCharger · 2026-10-16
- DIY benchmark ranks 18 models on subjective judgments, GLM-5.3 tops consensus match — arkuto · 2026-10-16
- Bindu Reddy: Google's Argon excels at complex doc writing at half the cost of Opus — bindureddy · 2026-10-16
- MAI-2 is 2x bigger than V4-Pro while V4.1F is 3x smaller: Microsoft's scaling ladder questioned — teortaxesTex · 2026-10-16
- Step 5 Preview hits DeepInfra day-zero: 600B MoE, 1M context, $1/M input tokens — StepFun_ai · 2026-10-16