timrogers

I wonder how this works under the hood and if it is significantly compromises security - no technical details in the article

It’s an incredible map - so many fun memories!

Tim from the Copilot coding agent team here. We've now disabled these tips in pull requests created by or touched by Copilot, so you won't see this happen again for future PRs.

We've been including product tips in PRs created by Copilot coding agent. The goal was to help developers learn new ways to use the agent in their workflow. But hearing the feedback here, and on reflection, this was the wrong judgement call. We won't do something like this again.

Reviewing AI output all day without the dopamine of creation is not a sustainable job description.

I agree that reducing engineers’ careers to code review will lead to burnout (amongst other problems).

But I think the reason we’re headed in this direction is precisely because creating with AI /can/ deliver “the dopamine of creation”.

It doesn’t deliver that hit for everyone - but it does for the half of engineers who are more excited about building new things than the act of coding.

Teams build more and ship faster because it’s so much easier to do that with AI - and it’s fun - and that leads to increased review load.

That would be the normal pattern. But you could certainly stop after the LLM picks the tool and provides the arguments, and not present the result back to the model.

The claim in the quote here is simply not true.

The travel agency is the one that collects your personal information - but it (unsurprisingly) immediately passes just about everything to the airline: name, date of birthday, phone number, email etc.

In general, the airline won’t get your payment details though.

GitHub PM here. We have tried this, but we weren't able to get results that we were satisfied with. Of course, you have to revisit these things regularly, as the models and wider state of the art are evolving so quickly!

Tim from the GitHub Copilot coding agent product team here!

@artdigital is on the money here. Our quick tip for beginners is to use `copilot-instructions.md` (which we can now generate for you <3), but for more serious use, we'd strongly recommend adding `copilot-setup-steps.yml`.

That gets you a deterministic setup - and for many teams, it'll be easy, as you can just copy and paste from existing Actions workflows.

PM for GitHub Copilot coding agent here!

Our asynchronous coding agent can run Docker in its GitHub Actions-powered development environment - for example it could start a Dockerized web server.

You can learn more about the agent at https://docs.github.com/en/copilot/concepts/coding-agent/cod....

Interestingly, the title refers to citizens but the body only refers to residents:

the AWS European Sovereign Cloud is operated only by personnel who are European Union (EU) residents located in the EU, subject to EU law.

The #5 contributor thing is a stat from a single repository where we’re building Copilot coding agent.

Humans are indeed in slots #1-4.

After hearing feedback from the community, we’re planning to share more on the GitHub Blog about how we’re using Copilot coding agent at GitHub. Watch this space!

At the moment, we're using Claude 3.7 Sonnet - but we're keeping our options open to experiment with other models and potentially bring in a model picker.

(Source: I'm on the product team for Copilot coding agent.)

Don't worry - this is 100% opt in. We've just added the ability to assign Copilot to an issue from `gh issue edit` and other similar commands.

(Source: I'm on the product team for Copilot coding agent.)

As we've built Copilot coding agent, we've put a lot of thought and work into our security story.

One of the things we've done here is to treat Copilot's commits like commits from a first-time contributor to an open source project.

When Copilot pushes changes, your GitHub Actions workflows won't run by default, and you'll have to click the "Approve and run workflows" button in the merge box.

That gives you the chance to run Copilot's code before it runs in Actions and has access to your secrets.

(Source: I'm on the product team for Copilot coding agent.)

Thanks for flagging this! That isn't a behavior I've seen before in testing, and I'd love to dig into it more to see what's happening.

Would you be able to drop me an email? My address is my HN login @github.com.

(I work on the product team for Copilot coding agent.)

At the moment, we're using Claude 3.7 Sonnet, but we're keeping our options open to change the model down the line, and potentially even to introduce a model picker like we have for Copilot Chat and Agent Mode.

The "1,000 pull requests contributed by Copilot" datapoint is specifically referring to Copilot coding agent over the past 2.5 months.

Pretty much every developer at GitHub is using Copilot in their day to work, so its influence touches virtually every code change we make ;)

But would you rather get paid to spend your time doing the interesting and enjoying work, or the mundane and boring stuff? ;) My hope is that agents like Copilot can help us burn down the tedious stuff and make more time for the big value adds.

Nice idea! We're going to try to get together a blog post in the next couple of weeks on how we're using Copilot coding agent at GitHub - including to build Copilot coding agent ;) - and having some live stats would be pretty sweet too.

Copilot only does work that has been assigned to it by a developer, and all the code that the agent writes has to go through a pull request before it can be merged. In fact, Copilot has no write access to GitHub at all, except to push to its own branch.

That ensures that all of Copilot's code goes through our normal review process which requires a review from an independent human.

Great question!

We started with Pro+ and Enterprise first because of the higher number of premium requests included with the monthly subscription.

Whilst we've seen great results within GitHub, we know that Copilot won't get it right every time, and a higher allowance of free usage means that a user can play around and experiment, rather than running out of credits quickly and getting discouraged.

We do expect to open this up to Pro and Business subscribers - and we're also looking at how we can extend access to open source maintainers like yourself.

What I'm most excited about is allowing developers to spend more of their time working on the work they enjoy, and less of their time working on mundane, boring or annoying tasks.

Most developers don't love writing tests, or updating documentation, or working on tricky dependency updates - and I really think we're heading to a world where AI can take the load of that and free me up to work on the most interesting and complex problems.

I think you're probably thinking of Copilot Workspace (<https://github.blog/news-insights/product-news/github-copilo...>).

Copilot Workspace could take a task, implement it and create a PR - but it had a linear, highly structured flow, and wasn't deeply integrated into the GitHub tools that developers already use like issues and PRs.

With Copilot coding agent, we're taking all of the great work on Copilot Workspace, and all the learnings and feedback from that project, and integrating it more deeply into GitHub and really leveraging the capabilities of 2025's models, which allow the agent to be more fluid, asynchronous and autonomous.

(Source: I'm the product lead for Copilot coding agent.)

Copilot pushes its work to a branch and creates a pull request, and then it's up to you to review its work, approve and merge.

Copilot literally can't push directly to the default branch - we don't give it the ability to do that - precisely because we believe that all AI-generated code (just like human generated code) should be carefully reviewed before it goes to production.

(Source: I'm the product lead for Copilot coding agent.)

We've been using Copilot coding agent internally at GitHub, and more widely across Microsoft, for nearly three months. That dogfooding has been hugely valuable, with tonnes of valuable feedback (and bug bashing!) that has helped us get the agent ready to launch today.

So far, the agent has been used by about 400 GitHub employees in more than 300 our our repositories, and we've merged almost 1,000 pull requests contributed by Copilot.

In the repo where we're building the agent, the agent itself is actually the #5 contributor - so we really are using Copilot coding agent to build Copilot coding agent ;)

(Source: I'm the product lead at GitHub for Copilot coding agent.)

Meta’s definition of quality is not the same as your definition of quality. For them, quality is (within reason) what drives “engagement” (aka time spent in their apps).

It might be that many people’s aesthetic sensibility is that AI-generated content is slop, but I’d still bet that tailored-perfectly-to-you content (and ads) will be highly engaging

I love to hear this as the PM for Copilot code review at GitHub!

We’re running a preview of the code review feature right now, and are looking forward to opening it to all paid subscribers soon.

If you’d like to try it sooner, I can hook you up - just email my HN username @github.com :)

I think I’d argue that the models are still a limiting factor for these kinds of tools - but there’s still also plenty of competitive space outside of models. The context you gather, the way you gather it and your prompting matters.

GitHub employee here

This does exist in GitHub Copilot - it’s called content exclusions: https://docs.github.com/en/copilot/managing-github-copilot-i...

I’m not sure if Cody has a similar feature, or if there’s any move towards a standardised solution.