Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GitHub Copilot Coding Agent

github.blog

Post reply on HN
Print view View original

61–70 of 372 posts

Re: GitHub Copilot Coding Agent

#61

Post by timrogers »

binarymax wrote: post #50
timrogers wrote: post #44

Earlier quoted context omitted.

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 contri…

So I need to ask: what is the overall goal of your project? What will you do in, say, 5 years from now?

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.

Re: GitHub Copilot Coding Agent

#62

Post by aaroninsf »

timrogers wrote: post #44
taurath wrote: post #13

> Copilot excels at low-to-medium complexity tasks in well-tested codebases, from adding features and fixing bugs to extending tests, refactoring, and improving documentation. Bounds bounds bounds bounds. The important part for humans seems to be maintaining boundaries for AI. If your well-tested codebase has the tests built thru AI, its probably not going to work. I think its somewhat telling that they can't share n…

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 contri…

Question you may have a very informed perspective on:

where are we wrt the agent surveying open issues (say, via JIRA) and evaluating which ones it would be most effective at handling, and taking them on, ideally with some check-in for conirmation?

Or, contrariwise, from having product management agents which do track and assign work?

Re: GitHub Copilot Coding Agent

#63

Post by ilaksh »

binarymax wrote: post #50
timrogers wrote: post #44

Earlier quoted context omitted.

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 contri…

So I need to ask: what is the overall goal of your project? What will you do in, say, 5 years from now?

That's a completely nonsensical question given how quickly things are evolving. No one has a five year project timeline.

Re: GitHub Copilot Coding Agent

#64

Post by OutOfHere »

Which model does it use? Will this let me select which model to use? I have seen a big difference in the type of code that different models produce, although their prompts may be to blame/credit in part.

Re: GitHub Copilot Coding Agent

#65

Post by ilaksh »

twodave wrote: post #23
taurath wrote: post #13

> Copilot excels at low-to-medium complexity tasks in well-tested codebases, from adding features and fixing bugs to extending tests, refactoring, and improving documentation. Bounds bounds bounds bounds. The important part for humans seems to be maintaining boundaries for AI. If your well-tested codebase has the tests built thru AI, its probably not going to work. I think its somewhat telling that they can't share n…

I feel like I saw a quote recently that said 20-30% of MS code is generated in some way. [0] In any case, I think this is the best use case for AI in programming—as a force multiplier for the developer. It’s for the best benefit of both AI and humanity for AI to avoid diminishing the creativity, agency and critical thinking skills of its human operators. AI should be task oriented, but high level decision-making and…

You might want to study the history of technology and how rapidly compute efficiency has increased as well as how quickly the models are improving.

In this context, assuming that humans will still be able to do high level planning anywhere near as well as an AI, say 3-5 years out, is almost ludicrous.

Re: GitHub Copilot Coding Agent

#66

Post by CSMastermind »

lukehoban wrote: post #45
muglug wrote: post #4

> Copilot excels at low-to-medium complexity tasks Oh cool! > in well-tested codebases Oh ok never mind

As peer commenters have noted, coding agent can be really good at improving test coverage when needed. But also as a slightly deeper observation - agentic coding tools really do benefit significantly from good test coverage. Tests are a way to “box in” the agent and allow it to check its work regularly. While they aren’t necessary for these tools to work, they can enable coding agents to accomplish a lot more on your…

In my experience they write a lot of pointless tests that technically increase coverage while not actually adding much more value than a good type system/compiler would.

They also have a tendency to suppress errors instead of fixing them, especially when the right thing to do is throw an error on some edge case.

Re: GitHub Copilot Coding Agent

#67

Post by shwouchk »

I played around with it quite a bit. it is both impressive and scary. most importantly, it tends to indiscriminately use dependencies from random tiny repos, and often enough not the correct ones, for major projects. buyer beware.

Re: GitHub Copilot Coding Agent

#68

Post by eterm »

Scene_Cast2 wrote: post #26
candiddevmike wrote: post #17

Earlier quoted context omitted.

> I also ended up blowing through $15 of LLM tokens in a single evening. This is a feature, not a bug. LLMs are going to be the next "OMG my AWS bill" phenomenon.

Cline very visibly displays the ongoing cost of the task. Light edits are about 10 cents, and heavy stuff can run a couple of bucks. It's just that the tab accumulates faster than I expect.

> Light edits are about 10 cents

Some well-paid developers will excuse this with, "Well if it saved me 5 minutes, it's worth an order of magnitude than 10 cents".

Which is true, however there's a big caveat: Time saved isn't time gained.

You can "Save" 1,000 hours every night, but you don't actuall get those 1,000 hours back.

Re: GitHub Copilot Coding Agent

#69

Post by 9wzYQbTYsAIc »

aaroninsf wrote: post #62
timrogers wrote: post #44

Earlier quoted context omitted.

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 contri…

Question you may have a very informed perspective on: where are we wrt the agent surveying open issues (say, via JIRA) and evaluating which ones it would be most effective at handling, and taking them on, ideally with some check-in for conirmation? Or, contrariwise, from having product management agents which do track and assign work?

Check out this idea: https://fairwitness.bot (https://news.ycombinator.com/item?id=44030394).

The entire website was created by Claude Sonnet through Windsurf Cascade, but with the “Fair Witness” prompt embedded in the global rules.

If you regularly guide the LLM to “consult a user experience designer”, “adopt the multiple perspectives of a marketing agenc”, etc., it will make rather decent suggestions.

I’ve been having pretty good success with this approach, granted mostly at the scale of starting the process with “build me a small educational website to convey this concept”.

Re: GitHub Copilot Coding Agent

#70

Post by binarymax »

ilaksh wrote: post #63
binarymax wrote: post #50

Earlier quoted context omitted.

So I need to ask: what is the overall goal of your project? What will you do in, say, 5 years from now?

That's a completely nonsensical question given how quickly things are evolving. No one has a five year project timeline.

Absolutely the wrong take. We MUST think about what might happen in several years. Anyone who says we shouldn’t is not thinking about this technology correctly. I work on AI tech. I think about these things. If the teams at Microsoft or GitHub are not, then we should be pushing them to do so.
Post reply on HN