LoRA LoRA: Fine-Tuning Without Retraining the Whole Model When prompting hits a ceiling, teams often assume fine-tuning means retraining billions of parameters on a GPU cluster. LoRA (Low-Rank Adaptation) is why that's no longer true. The idea Instead of updating a layer's full weight matrix W, LoRA freezes W and learns a
copilot Use Copilot's "Explain This" in Outlook We all get emails like this one: "Need the SOW sign-off before the Q4 true-up, otherwise the PO slips to the next FY." If you're new to a team, a client, or a field, a single line like that can send you through five
Token Tokens and Embeddings, Explained Simply A model doesn't read words. It reads tokens: pieces of text that can be a character, part of a word, a whole word, or punctuation. Spaces matter too, so "red", "Red", and " red" can all become different tokens (OpenAI, n.d.-a)
Claude Code Fighting "Lost in the Middle" Long-running AI agents have a well-documented failure mode: the further a piece of information sits from the start or end of the context window, the less reliably the model attends to it. This is the "lost in the middle" effect, and it's a big
G-Eval LLM-as-a-Judge: Grading AI Outputs With Another AI, Reliably If you're building anything with LLMs, at some point you need to answer "is this output actually good?" at a scale where a human can't read every response. The standard technique for this now is LLM-as-a-judge: you use a second LLM
reranking RAG Rerankers If you've built a retrieval-augmented generation (RAG) pipeline and found that answers are occasionally missing obvious context even though the right document is "in the knowledge base," the problem is usually the retrieval step, not the LLM. Standard vector search relies on bi-encoders: models
Claude Stop Routing Data Through Your LLM Here's a pattern worth stealing if you're building agents that connect to more than a handful of tools: code execution with MCP. The default way most agent frameworks use the Model Context Protocol is to load every connected tool's full definition into context up
