technicals

What are parameters and weights?

June 2, 2026 · 4 min read

PARAMETERS & WEIGHTSTraining just sets every knob.Each weight is one dial — turned dim or bright until the panel lands the answer.inputsoutputA model is millions of these dials; learning means nudging each one up or down.

Definition

Parameters are the internal numbers an AI model tunes during training to make accurate predictions, and weights are the main type, controlling how strongly each input influences the result.[1]

At a glance

The recipe analogy

Think of a cookie recipe: 2 cups flour, 1 cup sugar. Those numbers control the outcome; change them and you get different cookies. Parameters work the same way, except an AI has billions of them and learns the right values automatically by tasting its own results millions of times[4].

Why the count matters to you

Parameter count is a rough proxy for how much a model knows and can do. More parameters often means smarter output, but also more computing power, slower responses, and higher cost per use. A smaller, cheaper model is frequently the better business choice for routine tasks[3].

Bottom line

Parameters and weights are the learned numbers that make an AI work; their count signals capability but also cost, so bigger is not always better for your needs.

Connects to Computer Science

References

  1. What are Model Parameters? IBM www.ibm.com
  2. What are Model Weights in AI? Ultralytics www.ultralytics.com
  3. GPT-4. Wikipedia en.wikipedia.org
  4. What Are LLM Parameters? A Simple Explanation of Weights, Biases, and Scale. Towards AI towardsai.net