Notes on software engineering, shipping products, and building fast, maintainable web experiences.
LLMs are today’s most visible NLP technology, but NLP is the broader field. LLMs sit inside NLP—alongside classic methods, evaluation, linguistics, and production system design.
LLMs look like magic because they speak fluently—but under the hood they’re probabilistic token predictors trained on massive text. Here’s what they are, what they’re good at, and where they break.
RAG is a pattern that lets an LLM answer with your data by retrieving relevant context first, then generating a response grounded in that context.
A practical checklist of tools AI engineers use to ship reliable AI features: dev environments, data tooling, LLM stacks, evaluation, observability, and deployment.
A practical roadmap for turning AI hype into real engineering skills: product thinking, data + evaluation, LLM/RAG basics, and shipping responsibly.