Training vs inference

After this lesson you can: Say which costs money, which takes time, and which happens when you use ChatGPT.

First: What machine learning actually is

Watch

• AI Inference: The Secret to AI's Superpowers - IBM Technology, 11 min. A short IBM explainer on inference best matches the ChatGPT-use side of training versus inference.

Notes

Training is the expensive learning phase. Engineers feed a model many examples, run optimization, measure errors, and update the model’s internal numbers until it performs well enough. This can take hours, days, or months and usually needs specialized hardware and engineering effort. Once training finishes, the result is a model artifact: a fixed set of learned weights plus code that knows how to run them.

Unlock the full lesson notes, the exercises and the graded checkpoint - ₹5,000 once.