# Large language model (LLM)

> A model trained on enormous amounts of text to predict what comes next, which turns out to be enough to write, summarise, translate and reason through many tasks.

The training objective is unglamorous: given a stretch of text, predict the next piece. Done at sufficient scale, the model has to internalise grammar, facts, argument structure and a great deal about how people write in order to predict well, and those capabilities are what you use when you ask it to do something.

Two consequences follow from that and explain most surprises. The model has no separate store of facts it can check, so a plausible-sounding wrong answer is produced by exactly the same machinery as a right one. And it has no memory between calls: everything it knows about your conversation was sent to it again, as text, on every single request.

## Related terms

- https://dfieldsolutions.com/en/glossary/context-window.md
- https://dfieldsolutions.com/en/glossary/hallucination.md
- https://dfieldsolutions.com/en/glossary/fine-tuning.md
- https://dfieldsolutions.com/en/glossary/embedding.md

---

Source: https://dfieldsolutions.com/en/glossary/llm
DField Solutions — Dunakeszi, Hungary — dezso@dfieldsolutions.com
Booking: see https://dfieldsolutions.com/en/contact