From the course: Accelerate DevOps and Software Development with AI: Modern Tools and Workflows for Enhanced Software Delivery

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

What powers GitHub Copilot and ChatGPT?

What powers GitHub Copilot and ChatGPT?

From the course: Accelerate DevOps and Software Development with AI: Modern Tools and Workflows for Enhanced Software Delivery

Start my 1-month free trial Buy for my team

What powers GitHub Copilot and ChatGPT?

“

- Have you ever wondered what's actually powering tools like GitHub copilot or ChatGPT? They feel magical, but under the hood, there's a lot of complex engineering and training data at work and understanding just a bit of how they work can help you use them more effectively and more responsibly. Let's start with what they have in common. Both copilot and ChatGPT are powered by something called large language models, often abbreviated as LLMs. These are deep learning models trained on massive data sets made up of text, code, documentation, conversations, and more. The core engine behind both tools is a neural network architecture called a transformer. This architecture is excellent at understanding context, meaning that it can take a long piece of text, like a paragraph or a function definition and figure out how all the words or tokens relate to one another. That ability to track context is why these tools seem to…

Contents