Week 3: Behind the Scenes

Day 16: Training, Fine-Tuning, and Alignment

Day 16 of 2815 minGoal - Learn - Example - Practice - Checkpoint

Goal

Understand the stages that shape model behavior.

Learn

Pretraining teaches broad patterns from large datasets. Fine-tuning teaches a model to behave better for specific tasks or domains. Alignment methods use human feedback, preference data, safety rules, and evaluations to make outputs more helpful and less harmful. None of these stages make a model perfect.

Behind the scenes
AI tools are products wrapped around models, data, prompts, retrieval, safety systems, and user interfaces. The better you understand the wrapper, the better your results get.

Example

Example: in a real workflow, this idea helps you decide how to use AI carefully. For this lesson, connect the goal to one task you already do: understand the stages that shape model behavior..

Practice

Draw a simple pipeline: data -> pretraining -> fine-tuning -> safety/alignment -> app interface.

Checkpoint

Checkpoint
You can describe why two models can feel different even when both are chatbots.