You built the pipeline. Documents are chunked, embedded, and sitting in a vector store. Retrieval returns results. And your RAG answers still hallucinate in .NET, confidently telling users about a stu
Markdown supported · ⌘↵ to post
Coding Droplets
The point that a model handed context will use it whether or not it's relevant is the root cause people keep prompt-engineering around instead of fixing upstream. Two independent refusal layers is the part I'd emphasize, because a single relevance check tends to fail the same way the retriever did. Citations that carry their own scores are underrated too, since a low-confidence citation the user can click beats a fluent answer with nothing behind it.
Puneet Khandelwal
Always interesting to see how different approaches to data tracking can shape our understanding of ourselves