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.
![](https://github.blog/wp-content/uploads/2023/05/1200.630-Global-wLogo.png?resize=1200%2C630)
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!
Tags:
Written by
Related posts
![](https://github.blog/wp-content/uploads/2023/10/Collaboration-DarkMode-2.png?resize=400%2C212)
2024 is the biggest global election year in history. What’s at stake for developers?
GitHub is considering what is at stake for our users and platform, how we can take responsible action to support free and fair elections, and how developers contribute to resilient democratic processes.
![](https://github.blog/wp-content/uploads/2023/10/AI-DarkMode-2.png?resize=400%2C212)
GitHub named a Leader in the Gartner first-ever Magic Quadrant for AI Code Assistants
This year, as part of its annual Magic Quadrant series, Gartner published a first-of-its-kind report analyzing the state of play in the AI Code Assistants market–and named GitHub a Leader.
![AI in software development 2024 survey results with colorful graphics and percentages.](https://github.blog/wp-content/uploads/2024/08/ai-survey-header.png?resize=400%2C212)
Survey: The AI wave continues to grow on software development teams
We surveyed 2,000 people on software development teams at enterprises in the U.S., Brazil, India, and Germany about the use, experience, and expectations around generative AI tools in software development.