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

311–320 of 372 posts

Re: GitHub Copilot Coding Agent

#311

Post by skydhash »

Cthulhu_ wrote: post #262
skydhash wrote: post #128

Earlier quoted context omitted.

The market value good documentation. Anything critical and commonly used is pretty well documented (linux, databases, software like Adobe's,...). You can see how many books/articles have been written about those systems.

> Anything critical and commonly used is pretty well documented I'd argue the vast majority of software development is neither critical nor commonly used. Anecdotal, but I've written documentation and never got any feedback on it (whether it's good or bad), which implies it's not read or the quality doesn't matter.

Sometimes the code, if written cleanly, is trivial enough for anyone with a foundation in the domain so it can act like the documentation. And sometimes, only the usage is important, not the implementation (manual pages). And some other times, the documentation are the sandards (file formats and communication protocols). So I can get why no one took the effort to compile a documentation manual.

Re: GitHub Copilot Coding Agent

#312

Post by bearjaws »

bencyoung wrote: post #294

Some example PRs if people want to look: https://github.com/dotnet/runtime/pull/115733 https://github.com/dotnet/runtime/pull/115732 https://github.com/dotnet/runtime/pull/115762

That first PR is rough. Why does it have to wait for a comment to fix failing tests?

Re: GitHub Copilot Coding Agent

#313

Post by meindnoch »

PhilipRoman wrote: post #137
shwouchk wrote: post #67

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.

This is something I've noticed as well with different AIs. They seem to disproportionately trust data read from the web. For example, I asked to check if some obvious phishing pages were scams and multiple times I got just a summary of the content as if it was authoritative. Several times I've gotten some random chinese repo with 2 stars presented as if it was the industry standard solution, since that's what it said…

>On an unrelated note, it also suggested I use the "Strobe" protocol for encryption and sent me to https://strobe.cool which is ironic considering that page is all about making one hallucinate.

That's not hallucination. That's just an optical illusion.

Re: GitHub Copilot Coding Agent

#314

Post by cwsx »

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…

Is Copilot _enforced_ as the only option for an AI coding agent? Or can devs pick-and-choose whatever tool they prefer

I'm interested in the [vague] ratio of {internallyDevlopedTool} vs alternatives - essentially the "preference" score for internal tools (accounting for the natural bias towards ones own agent for testing/QA/data purposes). Any data, however vague is necessary, would be great.

(and if anybody has similar data for _any_ company developing their own agent, please shout out).

Re: GitHub Copilot Coding Agent

#315

Post by xur17 »

kookamamie wrote: post #292

Which GitHub subscription level is required for the agent? I found it very confusing - we have GH Business, with Copilot active. Could not find a way to upgrade our Copilot to the level required by the agent. I tried using my personal Copilot for the purpose of trialing the agent - again, a no-go, as my Copilot is "managed" by the organization I'm part of. Also, you will want to add more control over to who can assig…

I'm running into the same issue. I think you have to upgrade your entire organization to "enterprise", which comes with a per seat cost increase (separate from the cost of copilot).

Re: GitHub Copilot Coding Agent

#316

Post by dboreham »

skydhash wrote: post #168
throw1235435 wrote: post #148

Earlier quoted context omitted.

Its interesting that even people initially skeptical are now thinking they are on the "chopping block" so to speak. I'm seeing it all over the internet and the slow realization that what supposed to be the "top of the heap" is actually at the bottom - not because of difficulty of coding but because the AI labs themselves are domain experts in software and therefore have the knowledge and data to tackle it as a proble…

I don't think I'm on the chopping block because of AI capabilities, but because of executive shortsightedness. Kinda like moving to the Cloud eliminated sysadmins, but created DevOps, but in many ways the solution is ill-suited to the problem. Even in the early days of LLM-assisted coding tools, I already know that there will be executives who would said: Let's replace our pool of expensive engineers with a less expe…

That said, management generally never cared about quality and maintenance.

Re: GitHub Copilot Coding Agent

#318

Post by internet101010 »

worldsayshi wrote: post #100
literalAardvark wrote: post #98

Earlier quoted context omitted.

"We need to get 1000 PRs merged from Copilot" "But that'll take more time" "Doesn't matter"

I do agree that some scepticism is due here but how can we tell if we're treading into "moving the goal posts" territory?

When someone says that the number given is not high enough. I wouldn't consider trying to get an understanding of PR acceptance rate before and after Copilot to be moving the goal posts. Using raw numbers instead of percentages is often done to emphasize a narrative rather than simply inform (e.g. "Dow plummets x points" rather than "Dow lost 1.5%").

Re: GitHub Copilot Coding Agent

#319

Post by shakes_mcjunkie »

k3liutZu wrote: post #271
antihipocrat wrote: post #125

Earlier quoted context omitted.

That's exactly what senior executives who aren't coding are saying everywhere. Meanwhile, engineers are using it for code completion and as a Google search alternative. I don't see much difference here at all, the only habit to change is learning to trust an AI solution as much as a Stack Overflow answer. Though the benefit of SO is each comment is timestamped and there are alternative takes, corrections, caveats in…

> Meanwhile, engineers are using it for code completion and as a Google search alternative. Yep, that's the usefulness right now.

In my experience it's far less useful than simple auto complete. It makes things up for even small amounts of code that I have to pause my flow to correct. Also, without actually googling you don't get any context or understanding of what it's writing.

Re: GitHub Copilot Coding Agent

#320

Post by accurrent »

I wonder what the coding agent story will be for bespoke hardware. For instance I'd like to test somethings out on a specific gpu which isnt available on github. Can I configure my own runners and hope for the beat? What about bespoke microcontroller?
Post reply on HN