Large Language Models (LLMs)

A large language model (LLM)glossary×Large Language Model (LLM)A Large Language Model is an AI model trained on vast amounts of text data to understand and generate human-like language.Open glossary term→ is a type of AI systemglossary×SystemA system is a collection of interconnected components that work together to achieve a specific function or outcome.Open glossary term→ trained on vast amounts of text to understand and generate human language.

LLMsglossary×Large Language Model (LLM)A Large Language Model is an AI model trained on vast amounts of text data to understand and generate human-like language.Open glossary term→ learn patternsglossary×PatternA reusable solution to a common design problem.Open glossary term→ in language by processing enormous quantities of text — books, websites, articles, code, and more. From that training, they develop the ability to predict what comes next in a sequence of words, which is the core mechanism behind generating responsesglossary×ResponseA response is the data or result returned by a server after receiving a request.Open glossary term→.

When you type a question or promptglossary×PromptA prompt is the input or instruction given to an AI system to guide its output or response.Open glossary term→ into an AI tool, the LLM generates a responseglossary×ResponseA response is the data or result returned by a server after receiving a request.Open glossary term→ one token at a time, each step influenced by everything that came before it.

This means LLMsglossary×Large Language Model (LLM)A Large Language Model is an AI model trained on vast amounts of text data to understand and generate human-like language.Open glossary term→ are not retrieving pre-written answers. They are generating new text based on patternsglossary×PatternA reusable solution to a common design problem.Open glossary term→ learned during training.

LLMsglossary×Large Language Model (LLM)A Large Language Model is an AI model trained on vast amounts of text data to understand and generate human-like language.Open glossary term→ power most of the AI featuresglossary×FeatureA feature is a specific piece of functionality within a product that delivers value to users. It represents something users can do or experience as part of the overall product.Open glossary term→ people interact with today, from chatbots and writing assistants to searchglossary×SearchSearch is the functionality that allows users to find content or information by entering queries. It relies on indexing, metadata, and relevance algorithms to return useful results.Open glossary term→ tools, code generators, and product recommendation systems.

Understand when LLMsglossary×Large Language Model (LLM)A Large Language Model is an AI model trained on vast amounts of text data to understand and generate human-like language.Open glossary term→ are the right foundation. They are most relevant when:

They are less relevant when:

Understand the basic mechanism. LLMsglossary×Large Language Model (LLM)A Large Language Model is an AI model trained on vast amounts of text data to understand and generate human-like language.Open glossary term→ are trained using a processglossary×ProcessA process is a defined sequence of steps used to achieve a specific outcome.Open glossary term→ called next-token prediction. The modelglossary×ModelA model is a system or representation used to process data and generate outputs, often trained to perform specific tasks.Open glossary term→ is shown huge amounts of text and learns to predict what word or phrase comes next based on the context that precedes it.

Through billions of these predictions during training, the modelglossary×ModelA model is a system or representation used to process data and generate outputs, often trained to perform specific tasks.Open glossary term→ develops a deep representation of language, including grammar, facts, reasoning patternsglossary×PatternA reusable solution to a common design problem.Open glossary term→, and style.

When generating a responseglossary×ResponseA response is the data or result returned by a server after receiving a request.Open glossary term→, the modelglossary×ModelA model is a system or representation used to process data and generate outputs, often trained to perform specific tasks.Open glossary term→ samples from a probability distribution of likely next tokens, building the output word by word.

What this means for designers and product teams. LLMsglossary×Large Language Model (LLM)A Large Language Model is an AI model trained on vast amounts of text data to understand and generate human-like language.Open glossary term→ do not think or reason the way humans do. They generate plausible-sounding responsesglossary×ResponseA response is the data or result returned by a server after receiving a request.Open glossary term→ based on patternglossary×PatternA reusable solution to a common design problem.Open glossary term→ matching, which is why they can produce confident but incorrect answers.

The quality of an LLM's output is heavily influenced by how it is prompted. Vague or ambiguous inputs produce inconsistent outputs.

LLMsglossary×Large Language Model (LLM)A Large Language Model is an AI model trained on vast amounts of text data to understand and generate human-like language.Open glossary term→ have a knowledge cutoff — they do not know about events that occurred after their training was completed unless supplemented with tools like RAG.

Focus on:

Most issues come from: Treating an LLM like a database that retrieves facts will leadglossary×LeadA lead is a potential customer who has shown interest in a product or service, typically by providing contact information or engaging with content.Open glossary term→ to disappointment.

Understanding LLMsglossary×Large Language Model (LLM)A Large Language Model is an AI model trained on vast amounts of text data to understand and generate human-like language.Open glossary term→ gives you: