{"slug": "kimi-k2-6-reasoning-thinking-loop", "title": "Kimi K2.6 Reasoning thinking loop", "summary": "A user reported that Kimi K2.6 entered a reasoning thinking loop, repeating the same words roughly 1000 times, and that the stop button failed to cancel the request, which ran to the model's output limit and cost 0.21€. The user said the cancel button should terminate the request rather than letting it run to the output limit, and that the model should automatically terminate after detecting such a looping response.", "body_md": "I had this looping request (idk if the image above works) and tried to cancel it with the stop button, but that didn't work. Luckily it's just 0.21€, but still very unnecessary that it had to run until the very end of the model output limits instead of accepting my cancellation request or automatically terminating after detecting such a looping response (after 1000x same words).\n\nI expect the cancel button to cancel the request instead of running till the output limit.", "url": "https://wpnews.pro/news/kimi-k2-6-reasoning-thinking-loop", "canonical_source": "https://kagifeedback.org/d/10607-kimi-k26-reasoning-thinking-loop/6", "published_at": "2026-10-07 17:41:49+00:00", "updated_at": "2026-10-07 17:49:15.245027+00:00", "lang": "en", "topics": ["large-language-models", "ai-products"], "entities": ["Kimi K2.6"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/kimi-k2-6-reasoning-thinking-loop", "markdown": "https://wpnews.pro/news/kimi-k2-6-reasoning-thinking-loop.md", "text": "https://wpnews.pro/news/kimi-k2-6-reasoning-thinking-loop.txt", "jsonld": "https://wpnews.pro/news/kimi-k2-6-reasoning-thinking-loop.jsonld"}}