https://blog.margrop.net/en/tag/rag/ Recent content in RAG on Margrop Blog Hugo -- gohugo.io en-US Sun, 19 Jul 2026 20:30:00 +0800 https://blog.margrop.net/en/post/ai-hallucination-super-chengyu/ Sun, 19 Jul 2026 20:30:00 +0800 https://blog.margrop.net/en/post/ai-hallucination-super-chengyu/ <blockquote> <p><strong>The short answer</strong></p> <p>AI hallucination is not simply an occasional bug. It is a predictable risk of a system whose basic job is to generate the next likely token from context. The model can produce a fluent, confident, highly structured answer without having verified that every claim is supported by evidence.</p> <p>The easiest analogy is this: <strong>a large language model is a supercharged word-association player. It is exceptionally good at continuing a sentence. It is not automatically a fact-checker.</strong></p> </blockquote>