#fine-tuning

AI & Machine Learning

RAG, fine-tuning or long context: choosing how to give an LLM your knowledge

Ryan Pham · Aug 12, 2026 · 5 min read

Teams often reach for fine-tuning when they need retrieval, or build a retrieval pipeline when the whole corpus fits in the prompt. This guide compares RAG, fine-tuning and long context on freshness, cost, latency, citations and effort, with a decision table and examples.

AI & Machine Learning Bug Report

Fine-tuned LoRA adapter produces garbage in production: loaded on the wrong base model revision

Ryan Pham · Mar 25, 2026 · 6 min read

Our LoRA adapter for ticket summarisation worked in evaluation and produced repetitive nonsense in production. Serving loaded the base model by name without a revision, and the hub repository had been updated with a new tokenizer and weights. Pinning base revisions and a load-time smoke test fixed it.