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

  • Microsoft Revamps Fledgling AutoGen Framework for Agentic AI

    Only at v0.4, Microsoft's AutoGen framework for agentic AI -- the hottest new trend in AI development -- has already undergone a complete revamp, going to an asynchronous, event-driven architecture.

  • IDE Irony: Coding Errors Cause 'Critical' Vulnerability in Visual Studio

    In a larger-than-normal Patch Tuesday, Microsoft warned of a "critical" vulnerability in Visual Studio that should be fixed immediately if automatic patching isn't enabled, ironically caused by coding errors.

  • Building Blazor Applications

    A trio of Blazor experts will conduct a full-day workshop for devs to learn everything about the tech a a March developer conference in Las Vegas keynoted by Microsoft execs and featuring many Microsoft devs.

  • Gradient Boosting Regression Using C#

    Dr. James McCaffrey from Microsoft Research presents a complete end-to-end demonstration of the gradient boosting regression technique, where the goal is to predict a single numeric value. Compared to existing library implementations of gradient boosting regression, a from-scratch implementation allows much easier customization and integration with other .NET systems.

  • Microsoft Execs to Tackle AI and Cloud in Dev Conference Keynotes

    AI unsurprisingly is all over keynotes that Microsoft execs will helm to kick off the Visual Studio Live! developer conference in Las Vegas, March 10-14, which the company described as "a must-attend event."

Subscribe on YouTube