Delete discussions when blocking their author from your organization

When an organization administrator blocks an author of a discussion from a discussion page, they can now delete that discussion or all discussions that the user has authored in the organization.

Learn more in the documentation, and join the discussion in the community discussion to share your feedback.

Note: This feature has been rolled back. For the latest information about this capability, view this new post

Starting today, network requests for Copilot are routed based on a user’s Copilot subscription. Requests for Copilot Individual, Copilot Business, and Copilot Enterprise users now route through different endpoints.

This change enables Copilot Business and Copilot Enterprise customers to make sure all Copilot users on their networks are accessing Copilot through their Copilot Business or Copilot Enterprise subscription, and that all Copilot user data is handled according to the terms of their Copilot Business or Copilot Enterprise agreement. In essence, customers will be able to use their network firewall to explicitly allow access to Copilot Business or Copilot Enterprise, and/or block access to Copilot Individual.

In 90 days, on October 31, 2024 we will enable enforcement of the user’s subscription on the new endpoints, ensuring only Copilot Business users can connect to Copilot Business endpoints and only Copilot Enterprise users can connect to Copilot Enterprise endpoints.

Read more about subscription-based network routing here.

See more

Copilot Chat and pull request summary generation now use GPT-4o, bringing the performance of OpenAI’s latest flagship model to all developers.

Copilot Chat is available in Visual Studio, VS Code, JetBrains IDEs, GitHub Mobile apps, and GitHub.com.

To use the new GPT-4o model in your IDE, ensure you are using at least the minimum version of Copilot Chat specified here:

What this means for Copilot users

With this upgrade to GPT-4o, Copilot users will experience the following benefits:

  1. Faster response times – up to 55% faster TTFT (time to first byte)
  2. More accurate and reliable Copilot Chat responses – our testing showed a 60% increase in user satisfaction.

Commitment to quality

The upgrade process focused on our unwavering commitment to quality, safety, and security. Here’s what that entailed:

  1. Offline and online evaluation: We performed rigorous offline and online testing to ensure the model brings tangible benefits to users. This involved thorough benchmarking and running simulations of real-world software development scenarios to validate the improved performance and accuracy of GPT-4o.
  2. Red teaming: To preemptively address any potential safety issues, we conducted extensive red teaming exercises. These tests challenged the model to ensure it meets our high standards for safety and reliability in diverse coding environments.

We can’t wait to see what you create with the new GPT-4o-powered Copilot!

Let us know your feedback and join the discussion within the GitHub Community.

Happy coding!

See more