RolloAcademy
Under the hood

Training

The process where a model learns patterns from huge amounts of text, building the knowledge it later uses, fixed at a cut-off date.

Training turns text into a model Huge amounts of text feed a training step, which produces a model with patterns learned up to a cut-off. TRAINING TURNS TEXT INTO A MODEL Billions of documents Training A model patterns learned, fixed at a cut-off

Training is how a model learns. It reads enormous amounts of text and adjusts itself until it is good at predicting what comes next. That is where its "knowledge" comes from, not a database it looks things up in.

Two things follow. Training ends on a date, so the model has a knowledge cut-off and will not know newer events unless you add them. And what it learned reflects its training data, patterns and all, which is why the source you feed it still matters.

Often confused with: Learning in the moment. Training happened once, before you ever used the model; it does not learn from your chats as you go.

See it in a lesson: How generative AI works

Related terms

ModelMachine learningLarge language model

Further reading

← All terms