GitHub Copilot is powered by OpenAI Codex. It has been trained on natural language text and source code from publicly available sources, including code in public repositories on GitHub. It uses various elements of the context of your project to provide suggestions, including file content both in the file you are editing, as well as neighboring or related files within a project. It may also include the URLs of repositories or file paths to identify relevant context. The comments and code along with context are then used to synthesize and suggest individual lines and whole functions.

Training

GitHub Copilot’s Suggestions are all generated through AI. GitHub Copilot generates new code in a probabilistic way, and the probability that they produce the same code as a snippet that occurred in training is low. The models do not contain a database of code, and they do not ‘look up’ snippets.

Our latest internal research shows that about 1% of the time, a Suggestion may contain some code snippets longer than ~150 characters that matches the training set.

Previous research showed that many of these cases happen when GitHub Copilot is unable to glean sufficient context from the code you are writing, or when there is a common, perhaps even universal, solution to the problem.

Filter Public Code

To help you filter suggestions matching public code, we built a filter to help detect and suppress GitHub Copilot suggestions which contain code that matches public code on GitHub.

GitHub Copilot for Individual users have the choice to enable that filter during setup on their individual accounts. For GitHub Copilot for Business users, the Enterprise administrator controls how the filter is applied. They can control suggestions for all organizations or defer control to individual organization administrators. These organization administrators can turn the filter on or off during setup (assuming their Enterprise administrator has deferred control) for the users in their organization.

With the filter enabled, GitHub Copilot checks code suggestions with its surrounding code for matches or near matches (ignoring whitespace) against public code on GitHub of about 150 characters. If there is a match, the suggestion will not be shown to the user.

In addition, we have announced that we are building a feature that will provide a reference for suggestions that resemble public code on GitHub so that you can make a more informed decision about whether or not to use that code, as well as explore and learn how that code is used in other projects.

Just like when you write any code that uses material you did not independently originate, you should take precautions to understand how it works and ensure its suitability. These include rigorous testing, IP scanning, and checking for security vulnerabilities. You should make sure your IDE or editor does not automatically compile or run generated code before you review it.

Measures to keep in mind

You should take the same precautions as you would with any code you write that uses material you did not independently originate, and should take precautions to ensure its suitability. These include rigorous testing, IP scanning, and checking for security vulnerabilities. You should make sure your IDE or editor does not automatically compile or run generated code before you review it.

Hope that helps!