While the AI coding assistance market is getting busier and busier, GitHub Copilot remains our default choice and is used by many of our teams. Since we last wrote about GitHub Copilot, the most interesting improvements came in the chat feature. For instance, it's no longer necessary to clutter the code with comments as prompts; instead, an inline chat helps you prompt without writing a comment. The inline chat can also change code, not just write new lines. You can now also significantly expand the context of the chat when asking questions about your code by using the @workspace tag. This allows you to ask questions about the entire codebase, not just the open files. You can expand this context even further with the Copilot Enterprise version, which pulls in context from all repositories you host on GitHub. Finally, GitHub has started routing some chat requests to a more powerful GPT-4–based model, and availability of the chat in the popular Jetbrains IDEs is imminent (although still in private beta at the time of writing). These releases show that the pace of improvements in the space has not slowed down. If you tried a coding assistant last year and dismissed it, we recommend that you keep monitoring the features being released and give it another try.
GitHub Copilot is used by many of our teams to help them write code faster. Overall, most of our developers find it very useful and would be cross if we took it away from them. We've been collating and sharing many of our experiences with Copilot through a series on Generative AI and a guide on getting started with Copilot. Note that GitHub Copilot can be used with any codebase, not just codebases hosted on GitHub.
We're also excited that Copilot's chat feature from the Copilot X roadmap has become more widely available since we last featured it in the Radar. It is a powerful addition to Copilot's in-line assistance feature. The availability of a chat interface inside the IDE improves the discoverability of commonly searched information, and integration with the open editor context makes it easy to explore errors or ask the chat to assist with tasks related to the code in focus.
GitHub Copilot is an AI coding assistant, created by a collaboration between Microsoft and OpenAI. It uses machine learning models to generate suggestions based on the context of what a developer is working on. It features strong IDE integration and uses an existing codebase and editor context to create suggestions. Despite being billed as "your AI pair programmer" we would not call what it does "pairing" — we'd probably describe it as a kind of supercharged, context-sensitive Stack Overflow. When it correctly predicts what a developer is trying to do, it can be a powerful tool for getting stuff done. Like all LLM-based AIs, though, it has a tendency to hallucinate the use of plausible but nonexistent APIs and may introduce bugs through slightly faulty algorithms. We've had success generating code at the line, block and method level, as well as creating tests or infrastructure configurations. Interestingly, it works best when you use good naming practices, so it encourages more readable code.
AI tool capabilities are advancing rapidly, and we think it's sensible for organizations to try them. Some sales pitches for Copilot have claimed very high efficiency gains, but we remain skeptical: after all, writing code isn't the only thing that developers spend time on, and it's notoriously difficult to measure developer productivity in the first place. That said, Copilot is a fairly inexpensive tool; if it offers any productivity gain at all, it's probably worth it. Copilot X — in preview as of this writing — offers additional functionality and integration within a software creation workflow. Copilot has a "for business" offering, which provides more clarity around intellectual property issues as well as the ability to manage tool features centrally across an organization. We think these features are critical for enterprise adoption.
