Claude may have stopped showing summarized thinking traces, users say
emollick · x · 2026-07-25
Claude may have stopped showing summarized thinking traces
Emad Mostaque asks whether Claude has stopped surfacing its summarized thinking traces. If true, he argues that would be a meaningful loss because those traces help users diagnose errors and were themselves insightful.
The attached screenshots show a before/after comparison of a Claude interaction, where the earlier version exposed a concise thinking summary and the later one does not.
Related event: Claude Opus 5 Quietly Hides Thought Process, Frustrating Users(3 posts)→
More from Models
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- Terminal Bench v4: GLM-5.3 Leads at 41.9%, Kimi-K3 Underwhelms at 12.6% — Ok_Warning2146 · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11