Completion
A completion is what the model returns — not an "answer" in the human sense, but a continuation of the pattern started by your prompt. The model isn't checking facts, reasoning through a problem, or looking anything up. It's completing a sequence. This framing explains both why AI can produce strikingly helpful responses and why it can confidently generate completely wrong ones.
Videos explaining this concept
E007Notes on AI
What AI Receives When You Send a Prompt
A Prompt is commonly misunderstood as the sole input to an AI model. In reality, it is only the visible "Top Slice" of a larger input stack, best understood as a Prompt Sandwich.
E008Notes on AI
Is AI a Student or an Actor
AI outputs are completions — continuations of patterns, not fact-checked answers retrieved from a database. Like an improv actor following the "yes, and" rule, the model streams tokens to maintain the flow and never stops the scene. Modern models are trained to play the role of a truthful, helpful assistant, but the underlying mechanism is the same: predicting what comes next — and the model is performing truthfulness, not accessing it.
E009Notes on AI
What AI Is Good At vs Bad At
This episode introduces a practical framework for understanding when to use AI by framing it as a "special employee" with three distinct characteristics.
E010Notes on AI
The 5-Sentence Mental Model of GenAI
This episode provides a checkpoint after the foundational episodes, compressing the key concepts into five memorable sentences that serve as a mental compass for AI.
E011Notes on AI
Tokens
AI models don't read words — they read tokens, the basic unit of text a model processes. A token is close to a word but not identical: one word can be one token, several tokens, or several words can merge into one. Everything in AI is measured in tokens: input, output, context window size, and pricing. One token is roughly four characters in English; once you understand tokens, the limits and costs of AI stop feeling arbitrary.
E014Notes on AI
Context Window
The context window is the model's working space, not its memory — only what is currently visible can be reasoned about. Think of it as a desk: only the papers currently on it can be used, and as new papers arrive, old ones slide off the edge. This explains why instructions seem to disappear, why answers contradict earlier statements, and why long conversations slowly fall apart — the model isn't being careless, it simply no longer sees what you think it should remember.