Around the world, the adoption of Artificial Intelligence is growing exponentially. Its impact on the organizations’ growth is exceptional and decisive. AI is providing countless benefits and capabilities to organizations for a tremendous growth. Due to innovation in AI technology, developers use this tool to develop more effective and advanced software with ease. GitHub has also leveraged AI technology which helps developers’ community to perform better. Rajeev Ranjan, Editor, Digital Terminal exclusively talked to Shuyin Zhao, Sr. Director, Product Management, GitHub. Shuyin talked about their technology developments, AI, their offerings and much more. Read below the excerpts:
Rajeev: Please tell us about the technologies that GitHub is riding on in the current landscape.
Shuyin: Industry-wide, we’re now entering a new wave of innovation powered by AI. Ultimately, organizations that harness AI to empower their developers will win, and we recognize this. GitHub Copilot – the world’s first at-scale AI developer tool – is just the beginning of our vision to build an integrated, AI-powered GitHub that allows developers to build their best software. We plan to integrate AI into every aspect of the developer experience so developers can build their best software.
Rajeev: How is AI transforming the world? How do you see the massive shift towards adopting next-generation AI tools by large organizations?
Shuyin: The meteoric rise of generative AI has sparked industry-wide acceptance that the age of AI is here. In GitHub’s case, over 400+ organizations are already using GitHub Copilot – as of Feb 14 – and this is having a tangible impact on productivity, developer happiness, and the pace at which organizations can innovate.
Rajeev: Please briefly tell us about your AI developer tool ‘GitHub Copilot’. How does this solution bring greater benefits to enterprises?
Shuyin: GitHub Copilot is the world’s first at-scale AI developer tool. It sits within the editor as a simple extension, and draws context from a developer’s code to suggest new lines, entire functions, tests, and even complex algorithms. GitHub Copilot works with code and natural language prompts to offer multiple suggestions that can quickly be accepted or rejected — and it learns alongside developers to adapt to individual coding styles and conventions.
Since we launched GitHub Copilot, we’ve seen it redefine productivity for more than a million developers – our research shows that GitHub Copilot helps people code 55% faster. When you quantify that organization-wide, it's so exciting to imagine what that can do for enterprises – for their backlogs, and for developer velocity. Additionally, GitHub Copilot helps developers stay in the flow, focus on more satisfying work, and conserve mental energy, which leads to increased developer happiness. GitHub Copilot users code faster, focus on business logic over boilerplate, and do what matters most – building great software.
Rajeev: Please mention the new major capabilities of GitHub Copilot that boost developer productivity.
Shuyin: To improve the quality of GitHub Copilot’s code suggestions, we have updated the underlying Codex model resulting in large scale improvements to the quality of code suggestions and reduction of time to serve those suggestions to the users. When we first launched GitHub Copilot for Individuals in June 2022, more than 27% of developers’ code files on average were generated by GitHub Copilot.
Today, GitHub Copilot is behind an average of 46% of a developers’ code across all programming languages — and in Java, that number jumps to 61%. This work means that developers using GitHub Copilot are now coding faster than before thanks to more accurate and more responsive code suggestions.
We also launched an AI-based vulnerability prevention system that blocks insecure coding patterns in real-time to make GitHub Copilot suggestions more secure. Our model targets the most common vulnerable coding patterns, including hardcoded credentials, SQL injections, and path injections.
The new system leverages LLMs to approximate the behavior of static analysis tools — and since GitHub Copilot runs advanced AI models on powerful compute resources, it’s incredibly fast and can even detect vulnerable patterns in incomplete fragments of code. This means insecure coding patterns are quickly blocked and replaced by alternative suggestions.
Rajeev: What are your plans to further boost your performance in CY 2023?
Shuyin: We’re working on a number of exciting updates and new features, but we don’t have more to share at this time.