Category
Self-Hosted AI
AI you run and control: fine-tuning versus RAG on a self-hosted LLM, Qdrant hybrid search with BGE-M3, checking LLM OCR, and n8n MCP agents in production.
5 entries
Local LLM vs Cloud: Idle RAM Is Not Waste
Sam Altman calls RAM in personal computers wasteful at 5% use and wants maximum cloud utilization. In local LLM vs cloud, utilization is the landlord's metric.
Fine-Tuning vs RAG for a Self-Hosted LLM: Facts or Behaviour
Retrieve for facts, fine-tune for behaviour. In a Qwen3 demo, retrieval took a changed fact in 0.014 s while LoRA missed 3 of 8 facts, yet LoRA got a JSON contract right 10 of 10.
n8n MCP Agent Workflow in Production: Where the Agent Stops
In an n8n MCP agent workflow, the agent drafts and n8n holds publishing. Postiz's schedulePostTool takes a type of draft, schedule or now, so the limit is a parameter n8n must pin.
Claude API OCR on Financial-Aid Letters: Check the Math, Not the Reading
LLM OCR on financial-aid letters: a strict schema, deterministic normalising, sums that must reconcile, and flags for people. Reading the page is only the first check.
Qdrant and BGE-M3: Hybrid Search Without a Second Model
BGE-M3 produces dense and sparse vectors from one pass, so Qdrant can run hybrid search for production RAG without a second embedding model: prefetch both, fuse with RRF, filter early.