Instruction Tuning
A training step applied after pre-training that teaches a model to follow instructions — turning a model that just predicts text into one that actually does what you ask. Without instruction tuning, asking a model to "summarize this article" would more likely generate more article-like text than an actual summary. With it, the model understands the difference between being asked to do something and being asked to continue generating text. All modern AI assistants, including Claude, have gone through instruction tuning.
In practice
The base Claude model learned to predict text. Instruction tuning is what transformed it into an assistant that follows directions, answers questions helpfully, and understands that "summarize this" means you want a summary — not more text about summaries. It's the training phase that made the model useful for actual tasks.
Related concepts