61After fine-tuning an LLM on company data, do you still need RAG? How would you verify?▼hardNewOpenAICohere1 replies◆ premiumDecide whether retrieval can be removed after fine-tuning. Test changed facts, source support, access boundaries, and the cost of keeping answers current.Open full answer →
25Design per-user permissions for a RAG system over a company's documents. The CEO and an intern ask the same question.▼hardGleanMicrosoftSnowflake1 replies◆ premiumThe defining security design problem of enterprise RAG, and the reason Glean exists. Query-time ACL filtering, permission sync lag, and the leakage channels that survive naive designs: caches, citations, and the model itself.Open full answer →
