News

AI for GitHub Collaboration? Maybe Not So Much

No doubt GitHub Copilot has been a boon for developers, but AI might not be the best tool for collaboration, according to developers weighing in on a recent social media post from the GitHub team.

GitHub this morning posted, "How are you using AI to collaborate on GitHub?"

How are you using AI to collaborate on GitHub?
[Click on image for larger view.] How are you using AI to collaborate on GitHub? (source: X).

While it's only been live for about five hours at the time of this writing, it has attracted more than 40,000 views and 30 comments, many of which seem to be skeptical about using AI for collaboration.

Some example replies:

  • Not… 😅 As in, besides it is an LLM an not AI, but it is helpful at times... However, "collaborate" is far fetched IMHO. Or am I missing something?
  • Tried GitHub Copilot, but it's not free now, so I use ChatGPT to collaborate
  • Nope.
  • 🤔 hmm
  • I guess I'm participating in that copilot has slurped my code from github. Is that what you mean?
  • Sadly not in an efficient way. It would be awesome if GitHub Copilot would be available in Issues, Discussions and had integration APIs so that I can tell it to make multiple issues out of one and reference them directly, search for duplicates and automatically link them etc.
  • Not really [two of these]
  • Should I be using AI for this?
  • Stop.
  • I close Pull Request and Issues in my projects that are obviously AI-generated garbage. Thanks, LLMs, for making it easier for idiots to waste time of maintainers with useless changes that need more than a quick glance to look useless!

Along with the snarkiness and negativity, there were some more substantive responses like:

  • AI is revolutionizing how we handle CI/CD pipelines on GitHub! We're leveraging machine learning to automate testing and deployment processes, which significantly enhances our efficiency and reduces human error. It's exciting to see AI streamline our workflows and ensure more reliable releases.
  • Integrated copilot into IntelliJ and it helped very efficiently.
  • Mostly snippet

More responses are surely coming, though, so stay tuned.

About the Author

David Ramel is an editor and writer at Converge 360.

comments powered by Disqus

Featured

  • Hands On: New VS Code Insiders Build Creates Web Page from Image in Seconds

    New Vision support with GitHub Copilot in the latest Visual Studio Code Insiders build takes a user-supplied mockup image and creates a web page from it in seconds, handling all the HTML and CSS.

  • Naive Bayes Regression Using C#

    Dr. James McCaffrey from Microsoft Research presents a complete end-to-end demonstration of the naive Bayes regression technique, where the goal is to predict a single numeric value. Compared to other machine learning regression techniques, naive Bayes regression is usually less accurate, but is simple, easy to implement and customize, works on both large and small datasets, is highly interpretable, and doesn't require tuning any hyperparameters.

  • VS Code Copilot Previews New GPT-4o AI Code Completion Model

    The 4o upgrade includes additional training on more than 275,000 high-quality public repositories in over 30 popular programming languages, said Microsoft-owned GitHub, which created the original "AI pair programmer" years ago.

  • Microsoft's Rust Embrace Continues with Azure SDK Beta

    "Rust's strong type system and ownership model help prevent common programming errors such as null pointer dereferencing and buffer overflows, leading to more secure and stable code."

  • Xcode IDE from Microsoft Archrival Apple Gets Copilot AI

    Just after expanding the reach of its Copilot AI coding assistant to the open-source Eclipse IDE, Microsoft showcased how it's going even further, providing details about a preview version for the Xcode IDE from archrival Apple.

Most   Popular

Subscribe on YouTube

Upcoming Training Events

0 AM