Skip to content
ReviewRamble

The weekly brief

AI, reviewed, in your inbox.

  • New reviews of tools, models, MCP servers and repos, with the verdict up front
  • Re-checked prices and ratings when something changes
  • New analysis pieces as they are published

Models, agents, MCP servers and the tools actually worth your time.

One email a week. Unsubscribe with the link in any brief. How we use your email

Large language model

A large language model (LLM) is a neural network with billions of parameters, trained on large amounts of text to predict the next token, which lets it write, answer questions, summarise and follow instructions.

Also called: LLM, LLMs

By Divya Sharma · Checked Nov 15, 2026 · How we review

An LLM is the engine behind chat assistants, coding agents and most text features in AI products. You send it text, it returns text, one token at a time.

How it works

Almost every current LLM uses the transformer architecture. During pretraining it reads a very large text corpus and learns to predict the next token from everything before it. That simple objective produces a model that can translate, answer questions and write code. Further training, such as fine-tuning and RLHF, turns the raw model into an assistant that follows instructions.

What "large" means

There is no fixed cut-off. GPT-3, described in 2020, had 175 billion parameters, and the label stuck to models of that scale and beyond. Models with a few billion parameters are usually called small language models.

Limits

An LLM only knows what was in its training data up to its knowledge cutoff, and it can state false things fluently. It also sees only what fits in its context window. Builders usually add retrieval, tools or checks around the model rather than trusting raw output. Compare current models in the models directory.

Related terms

Token (LLM)
A token (LLM) is the basic unit of text a language model reads and writes, often a word, part of a word, a punctuation mark or a byte. Prices, speed and context limits are all counted in tokens.
Transformer (architecture)
The transformer is a neural network architecture, introduced in 2017, that processes sequences using attention instead of recurrence. It is the basis of nearly all current large language models and many image and audio models.
Small language model
A small language model (SLM) is a language model with relatively few parameters, usually a few billion or fewer, built to run on a laptop, phone or single GPU at lower cost than a large model.
Pretraining
Pretraining is the first and largest stage of training a model, where it learns general patterns from a very large unlabelled dataset, usually by predicting the next token, before any task-specific tuning.
Context window
A context window is the maximum amount of text, counted in tokens, that a language model can consider at once, covering the system prompt, conversation, documents, tool results and the response it writes.
Hallucination (AI)
A hallucination is output from an AI model that sounds fluent and confident but is false, unsupported by its sources or made up, such as an invented citation, quote, statistic or API function.

Sources