Head over to our on-demand library to view sessions from VB Transform 2023. Register Here
GitHub’s latest innovation in generative AI and GPT-4, Copilot X, is expanding its reach to enterprise companies and organizations. Today, the company announced the limited public beta release of GitHub Copilot Chat. With this, GitHub aims to integrate a context-aware conversational assistant directly into integrated development environments (IDE) like Microsoft Visual Studio and VS Code.
According to GitHub, developers will be able to effortlessly tackle complex tasks through simple prompts using Copilot Chat. The company asserts that this will empower every development team member, regardless of experience level, to build complete applications or debug extensive codebases in minutes rather than days.
“Unlike a general-purpose generative AI chat assistant, Copilot Chat is built specifically for developer scenarios and is contextually aware of the code a developer has typed and what error messages are shown because it is right there with them in their code editor/IDE, where they spend most of their time coding,” Mario Rodriguez, VP of product management at GitHub, told VentureBeat.
Rodriguez stated that the company’s latest offering is an AI pair programmer, designed explicitly to assist developers with numerous tasks, such as starting a file in an unfamiliar coding language or framework, autocompleting boilerplate code, and conducting debugging and writing unit tests.
Event
VB Transform 2023 On-Demand
Did you miss a session from VB Transform 2023? Register to access the on-demand library for all of our featured sessions.
Register Now
GitHub claims the new offering will democratize software development, improving developer teams’ productivity and satisfaction.
“Most AI developer tools are either in the experimental stages or have yet to be proven at scale, whereas Copilot Chat builds on GitHub Copilot, which over 1 million developers already trust,” said GitHub’s Rodriguez. “So we’ve benefited from being first to market, defining how AI can best improve developers’ workflow, and refining GitHub Copilot based on feedback from such a broad user base.”
Providing developer assistance through contextual understanding
GitHub said that Copilot Chat surpasses the functionality of a typical chat window. It can comprehend the code a developer has written and interpret the error messages that appear. The company asserts that, unlike generic generative AI chat assistants, Copilot Chat demonstrates contextual awareness, integrating concepts that are effective for general-purpose AI and tailoring them to developers’ specific environments.
“Copilot Chat is contextually aware of what a developer is trying to do at any given time. That context allows it to provide guidance specifically tailored to the user rather than offering general tips that may not apply to that scenario,” Rodriguez told VentureBeat.
GitHub says that previously, developers lacked a straightforward method to inquire or obtain additional context. With Copilot Chat, they can access immediate and context-specific support directly in their Editor/IDE.
“You can ask Copilot to propose a fix for the bugs in your code. By looking at your comment and comparing it to the code, Copilot will not only recognize errors and provide context on what went wrong, but it will also propose fixes that will address the issues,” said Rodriguez.
The AI model’s contextual approach addresses the challenge of maintaining developers’ workflow amid the increasing complexity of programming over the past two decades. Factors contributing to this complexity include the proliferation of languages, cloud computing, programming frameworks, and diverse services.
For instance, developers need not pull up a regular expression translator when faced with poorly documented regular expressions. Instead, they can simply highlight the code and request explanations from Copilot Chat.
Beyond comprehension
Beyond code comprehension, developers can enhance their code by instructing Copilot Chat to “improve code readability,” “add more comments” or “separate the validation function.”
“Users can ask Copilot Chat for assistance with coding challenges. If Copilot Chat doesn’t fully answer your question with its first response, you can continue to ask follow-up questions, request clarifications, and more,” said Rodriguez. “This conversational element makes Copilot Chat so powerful — it’s not a one-and-done tool; it’s a conversational assistant that stays with you through your entire coding process.”
The company claims astounding productivity gains with GitHub Copilot. In a controlled study, GitHub discovered that developers accomplished tasks 55% faster using GitHub Copilot. Early research indicates that an average of 46% of code across all programming languages is constructed with GitHub Copilot, a number that surges to 61% among Java developers.
Security check
Rodriguez stated that users can ask Copilot Chat to review their code within the IDE itself. During this review process, Copilot Chat may identify potential security issues and offer suggestions for remediation.
“What makes Copilot Chat particularly unique for this scenario is that results are personalized to the user’s code, whereas if a developer had searched on Stack Overflow or Google, they might have run across dozens of variations, patterns and flavors for solutions to bugs and the one relevant to the user might not even be one of them,” explained Rodriguez. “Ultimately, this capability can reduce the number of vulnerabilities found in security scans.”
GitHub said developers can converse with Copilot Chat using natural language, just as a human programmer, enabling discussions about complex concepts. The company asserts that this approach surpasses conventional methods of search and documentation reading.
“Instead of stopping what they’re doing to look up a code snippet’s functionality, they can just ask Copilot Chat and get an answer right in the IDE. It saves time and makes coding more interactive and engaging,” Rodriguez told VentureBeat. “We also believe Copilot Chat will lower barriers to entry and help beginner programmers upskill faster.”
VentureBeat’s mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. Discover our Briefings.