Start here. What AI, machine learning, and large language models actually are — tokens, embeddings, and how a model turns your words into an answer.
Untangle the three terms everyone mixes up. AI is the goal, machine learning is the main method, and deep learning is the technique behind today's chatbots — with clear examples of each.
Open lesson →The engine inside ChatGPT and Claude, explained without the maths. An LLM is a next-word predictor trained on huge amounts of text — which is exactly why it's so capable and why it sometimes makes things up.
Open lesson →Tokens are how models read, write, and bill. Learn what a token is, why the 'context window' limits what a model can consider at once, and how both directly shape your AI costs.
Open lesson →How AI turns words into numbers that capture meaning. Embeddings are the quiet workhorse behind search, recommendations, and RAG — understand them and a lot of AI suddenly makes sense.
Open lesson →Two very different phases with very different price tags. Training builds the model once at huge expense; inference is every answer it gives afterwards — and inference is the bill you pay daily.
Open lesson →