GPT — Generative Pre-trained Transformer

Fact

A Transformer language model pre-trained first, then used to generate text.

In Plain Words

GPT is like a kid after a summer in the library. Give it “Once upon a time,” and it keeps the story train going.

You meet it in chatbots and writing tools. It also powers code helpers and many big AI products.

Related Concepts

• Transformer architecture
• Pretraining
• Generative Pre-trained Transformer 3
• Large Language Model

Transformer
GPT is built on Transformer and became a main branch of that design.

Pretraining
GPT starts with large-scale Pretraining, then gains general text skills.

GPT-3
GPT-3 brought GPT into public view and made it a hot topic.

LLM
GPT is a classic member of the LLM family.