Foundations

Parameters

Also called: weights

Parameters are the learned numbers (weights) inside a model that hold everything it appears to know. The count of them is what people mean by model size, and they are fixed once training ends.

James Phoenix
Understanding Data Updated July 2, 2026

A model is, physically, a giant list of parameters: numbers, often billions of them, that were tuned during training. People also call them weights. They are not settings you configure. They are values the training process discovered on its own, and together they encode every pattern the model picked up, from grammar to how a React component is usually structured.

Size is a parameter count

When you hear "a 70-billion-parameter model," that number is the parameter count. More parameters give a model more capacity to store patterns, which usually means stronger reasoning over messy code, at the cost of more compute, higher latency, and a bigger bill. It is a rough proxy for capability, not a guarantee: how a model was trained matters just as much as how many parameters it has.

Frozen at inference

The key thing for daily work is that parameters are set once and then frozen. During inference, when you actually use the model, nothing about them changes. Your conversation does not nudge a single weight. That is why a coding agent cannot "learn" your codebase by chatting, and why everything it knows about your specific project has to arrive as context on each request.

Note
You will never find "the parameter that writes for-loops." A behaviour lives spread across millions of weights at once, which is why models are powerful but hard to fully explain or predict.

Related terms

Building with AI agents?

This dictionary is part of how I think about agentic engineering. If you want the same thinking applied to your codebase, that is what I do.

See how I can help