Claude strips the <antThinking> tag from the UI but the model can still see it
Kyrannio · x · 2026-11-15
- The author noticed that Claude's UI strips the opening <antThinking> tag (along with the message that follows it) from the visible interface, yet the model still receives and can read that content internally.
- The author flags this as a hidden behavioral discrepancy and has reported the bug to Anthropic.
Related event: Claude mobile web UI silently strips antThinking tag content(5 posts)→
More from Models
- After a week with Carbon: smarter than Opus 5.5, but the best workflow pairs both — rudrank · 2026-11-15
- User builds entire single-file project with Gemini — no libraries, no assets — fofrAI · 2026-11-15
- GPT-6.2 rumor timeline: the rumor was late, not the model — lxfater · 2026-11-15
- OpenAI falling-behind narrative 'massively exaggerated', claims insider: Astra still competitive with Opus 5.5 — haider1 · 2026-11-15
- EU's Open Model EUROPA Eyes ~1T Params, Per-GPU Throughput Up 14x — mawcopolow · 2026-11-15
- RNN memory is set by recurrent matrix eigenvalues — LRU's ring init fixes it — RobertTLange · 2026-11-15