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 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.
How? There are two setups, either you book with an agency, which then forwards your data to the airline, or you book directly with an airline. In both cases, you have a more or less fixed amount of data collected, due to legal requirements. But the agency will usually act as a proxy, only forwarding the absolute necessary information, and using some on their own (like form of payment or contacts), often even send replacement-data or their own to the airline.
So it's absolutely true that in certain common setups, the airline is not the one collecting and holding most information. But, this comes with the price that more parties are holding your information.
And agencies are often going through a CRS or even through a middleman to the CRS, not booking directly with the airline, so there is a good chance of a third or even fourth party also holding your information. Though, technically this can also depend on the agency, airline and type of flight. With Charter- and Lowcost-flights it can happen that the agency is going directly to the airline, hacking their way around the airlines' website. But this is getting shoot down in the last years but those airline, and not obvious from the outside.
Oh, and historically speaking, it used to be that agencies were often collecting more personal information than laws demanded, while airlines went with the absolute necessary stuff. So maybe the article was meaning this aspect too.
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.
Our asynchronous coding agent can run Docker in its GitHub Actions-powered development environment - for example it could start a Dockerized web server.
Always was. Its telling that they think that they were not previously subject to EU laws when their EU subsidiary did business with someone located in the EU.
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.)
I was trying to find information on this on the internet and couldn't find any, thanks for providing. Interestingly enough Copilot coding agent on github.com repeatedly could not complete css changes correctly, when I switched to Agent mode in the project IDE with Claude 3.7 it was able to complete it in one round, so I assumed that there was a different model.
In my experience using Claude Sonnet 3.7 in GitHub Copilot extension in VSCode, the model produced hideously verbose code, completely unnecessary stuff. GPT-4.1 was a breath of fresh air.
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.)
The announcement https://github.blog/news-insights/product-news/github-copilo... seems to position GitHub Actions as a core part of the Copilot coding agent’s architecture.
From what I understand in the documentation and your comment, GitHub Actions is triggered later in the flow, mainly for security reasons.
Just to clarify, is GitHub Actions also used in the development environment of the agent, or only after the code is generated and pushed?
reply