Smarter, more efficient coding: GitHub Copilot goes beyond Codex with improved AI model

We’re thrilled to announce two major updates to GitHub Copilot code Completion’s capabilities that will help developers work even more efficiently and effectively.

|
| 2 minutes

The magic of GitHub Copilot just got even better with an improved AI model and enhanced contextual filtering. These improvements give developers more tailored code suggestions that better align with their specific needs, and are available for both GitHub Copilot for Individuals and GitHub Copilot for Business.

Read on to learn more about these exciting updates and how they can help you take your coding skills to the next level.

Improved AI model goes beyond Codex for even faster suggestions

The improved AI model behind GitHub Copilot goes beyond the previous OpenAI Codex model, offering even faster code suggestions to developers. It was developed through a collaboration between OpenAI, Microsoft Azure AI, and GitHub, and offers a 13% latency improvement over the previous model.

This means that GitHub Copilot generates code suggestions for developers faster than ever, which promises to drive a substantial increase in overall productivity.

Enhanced Contextual Filtering for more tailored code suggestions

In addition to the improved AI model, we’ve implemented more sophisticated context filtering that takes into account a wider range of a developer’s context and usage patterns. With the update, GitHub Copilot filters prompts and suggestions more intelligently, so developers get more relevant code completions for their specific coding tasks.

This has resulted in a +6% relative improvement in code acceptance rate, allowing developers to focus even more on the creative aspects of their work rather than getting bogged down in tedious coding tasks. The productivity gain also allows developers to tackle more ambitious projects and bring their ideas to life more quickly.

Unlock new levels of productivity and satisfaction with GitHub Copilot

The improved AI model and the new context filtering offer 13% latency improvement and 6% relative improvement in code acceptance rate, building upon the productivity gains developers have come to expect while using GitHub Copilot. With these improvements, developers can expect to stay in the flow and work more efficiently than ever, leading to faster innovation with better code. They’ll also find more satisfaction with their work, given research that shows minimizing disruptions and staying in the flow have a tangible impact on developer happiness.

At GitHub, we’re committed to continuing to improve the developer experience with GitHub Copilot. We have some exciting plans in the works and will continue to share news on our blog and Changelog. Whether you’re a seasoned pro or just starting out, GitHub Copilot can help you take your coding skills to the next level–and we can’t wait to see what you’ll build with it!

Written by

Related posts