Massive language models trained to understand and generate text.
A Large Language Model (LLM) is a type of neural network trained on massive amounts of text (petabytes of data) to predict the next word in a sequence. This predictive capability, at scale, allows the model to understand nuance, context, languages, and logic, enabling it to write essays, summarize text, translate languages, and write code.
How Interlinked uses it
The Interlinked worker is built on top of frontier LLMs, but the model itself is not the product. The product is the workflow and the business context. The LLM only generates responses within the scope of the workflow you published and the business data you configured — it does not invent order statuses, appointments, or prices that are not in your catalog or calendar.