November 8, 2023 at 12:15PM
GitHub has announced the public preview of three new AI-powered features in GitHub Advanced Security. These features include AI-generated fixes for code alerts, identification of leaked passwords, and improved security overview dashboards. Additionally, GitHub released its Octoverse report, revealing a significant increase in developers building open source generative AI projects. The report shows a doubling of generative AI projects on GitHub in the first half of 2023, with developers progressing from research to using pre-trained models and APIs to create AI-powered applications.
GitHub has announced the public preview of three new AI-powered features in GitHub Advanced Security. These features, available for GitHub Enterprise Cloud and Enterprise Server customers, aim to help maintain and improve the quality of code. One of these features is an autofix capability where AI-generated fixes will be provided for CodeQL, JavaScript, and TypeScript alerts. GitHub also announced the use of the latest LLMs (large language models) to identify leaked passwords with fewer false positives as part of its secret scanning program. Additionally, the security overview dashboard has been updated to provide better analysis and visibility of security alerts and posture to security managers and administrators.
In another development, GitHub’s Octoverse report reveals an increasing number of developers are building open source generative AI projects. The number of generative AI projects on GitHub has more than doubled in the first half of 2023 compared to the entire year of 2022. Developers are now progressing from research to using pre-trained models and APIs to create generative AI-powered applications. GitHub expects open source developers to drive the next wave of AI innovation on its platform. Interestingly, the top 20 open source generative AI projects on GitHub are currently owned by individuals, but the platform expects organizations to start using pre-trained AI models as well. Contributions to generative AI projects on GitHub have seen a 148% year-over-year growth, with the US, India, and Japan leading the trend.
GitHub also announced the adoption of LLMs for GitHub Copilot, the AI developer tool. In December, users of Copilot will have access to Copilot Chat, which uses LLMs to help developers with error identification and code debugging. Copilot Chat will be available as part of the existing GitHub Copilot subscription and will also be offered at no cost to verified teachers, students, and maintainers of popular open source projects.