LLM
Model Bahasa Besar
A model trained on a huge amount of text to predict the next token. The engine behind most AI products.
An LLM is a neural network trained on a very large corpus of text, code, and other documents, with one objective: predict what comes next. Scale that up and you get behaviour that looks like understanding. Scale it up further, add instruction tuning, and you get something that can hold a conversation, follow a format, and act inside a harness.
The useful mental model is not "a database that answers questions" but "a very good next-token predictor that has read a lot". That model explains both its strengths and its failure modes: it can write an API call it has never seen, and it can also invent one.
Related terms
Model
The trained file of learned parameters that turns input into output.
Token
The unit a model reads and writes. Roughly word-sized, but not exactly.
Context Window
Everything the model sees on one request. Finite, and it decides what fits.
Transformer
The neural network design behind nearly every modern language model.
Hallucination
Output that is fluent and wrong. Two different problems hide under one word.
Want this working inside your team?
It starts with one conversation about your workflow.