SFT (supervised fine-tuning)

Fine-tuning on human-written prompt/answer pairs so a raw next-token predictor learns the shape of an answer. The cheapest, largest step from base model to assistant.

The trick that makes SFT work is loss masking: the loss counts only over the answer tokens, never the prompt. The model learns to *produce* answers, not to reproduce questions.

Companion explanation in Step by Token, chapter 8.