EN
Start free
Start free

What is a large language model (LLM)?

A large language model (LLM) is an AI system trained on very large amounts of text to predict and generate language. It is the technology behind AI assistants that can answer questions, write, summarise and translate. Its answers can be fluent and still wrong.

Last updated

In more detail

Chat assistants, writing tools and AI search features are all built on large language models, so it helps a marketer to know roughly how they work. A model learns patterns from its training text and then produces a reply one piece at a time, choosing what is likely to come next. It does not look facts up in a database unless it has been connected to a search tool or to documents. That explains both its fluency and its errors. Used well, a model drafts copy, rewrites for tone, summarises long documents, suggests ideas and translates, with a person checking the result. The common mistake is treating the output as verified. A model can state something false in a confident voice, and it may know nothing about events after its training ended. Another mistake is pasting confidential information into a tool without checking how the provider stores and uses it.

Where Wonib fits

Wonib works in the browser, and inside Claude and ChatGPT as a connected tool.

Put the words into practice

Wonib learns your brand once, then makes the posts, pictures, copy, decks and documents in it, checked against the brand before you see them. Start free with 1,000 credits, no card needed.

Last updated

Start free with 1,000 credits

No card needed. Sign up with Google or your email, confirm it, and make your first piece in minutes.

Continue with Google

or

Already have an account? Sign in