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

251–260 of 372 posts

Re: GitHub Copilot Coding Agent

#251

Post by rcarmo »

gen220 wrote: post #150
BeetleB wrote: post #29

Earlier quoted context omitted.

> I also ended up blowing through $15 of LLM tokens in a single evening. Consider using Aider, and aggressively managing the context (via /add, /drop and /clear). https://aider.chat/

I, too, recommend aider whenever these discussions crop up; it converted me from the "AI tools suck" side of this discussion to the "you're using the wrong tool" side. I'd also recommend creating little `README`'s in your codebase that are mainly written with aider as the intended audience. In it, I'll explain architecture, what code makes (non-)sense to write in this directory, and so on. Has the side-effect of bein…

There is a better way than just READMEs: https://taoofmac.com/space/blog/2025/05/13/2230

Re: GitHub Copilot Coding Agent

#252

Post by rcarmo »

mattlondon wrote: post #235
gen220 wrote: post #150

Earlier quoted context omitted.

I, too, recommend aider whenever these discussions crop up; it converted me from the "AI tools suck" side of this discussion to the "you're using the wrong tool" side. I'd also recommend creating little `README`'s in your codebase that are mainly written with aider as the intended audience. In it, I'll explain architecture, what code makes (non-)sense to write in this directory, and so on. Has the side-effect of bein…

Why create READMEs and not just comments in the code?

Comments are not easy for the LLM to refer to, ironically: https://taoofmac.com/space/blog/2025/05/13/2230

Re: GitHub Copilot Coding Agent

#253

Post by rcarmo »

imiric wrote: post #146
SkyPuncher wrote: post #97

Earlier quoted context omitted.

I loathe using AI in a greenfield project. There are simply too many possible paths, so it seems to randomly switch between approaches. In a brownfield code base, I can often provide it reference files to pattern match against. So much easier to get great results when it can anchor itself in the rest of your code base.

The trick for greenfield projects is to use it to help you design detailed specs and a tentative implementation plan. Just bounce some ideas off of it, as with a somewhat smarter rubber duck, and hone the design until you arrive at something you're happy with. Then feed the detailed implementation plan step by step to another model or session. This is a popular workflow I first read about here[1]. This has been the m…

Here’s my workflow, it takes that a few steps further: https://taoofmac.com/space/blog/2025/05/13/2230

Re: GitHub Copilot Coding Agent

#254

Post by rcarmo »

jagged-chisel wrote: post #201

I’ve been trying to use Copilot for a few days to get some help writing against code stored on GitHub. Copilot has been pretty useless. It couldn’t maintain context for more than two exchanges. Copilot: here’s some C code to do that Me: convert that to $OTHER_LANGUAGE Copilot: what code would you like me to convert? Me: the code you just generated Copilot: if you can upload a file or share a link to the code, I can h…

Be more methodical, it isn’t magic: https://taoofmac.com/space/blog/2025/05/13/2230

Re: GitHub Copilot Coding Agent

#255

Post by Tteriffic »

adamsb6 wrote: post #232
shepherdjerred wrote: post #114

Earlier quoted context omitted.

[flagged]

There's a large group of people that claim that AI tools are no good and I can't tell if they're in some niche where they truly aren't, they don't care to put any effort into learning the tools, or they're simply in denial.

Some of each

Re: GitHub Copilot Coding Agent

#256

Post by rcarmo »

quantadev wrote: post #104

I love Copilot in VSCode. I have it set to use Claude most of the time, but it let's you pick your fav LLM, for it to use. I just open the files I'm going to refactor, type into the chat window what I want done, click 'accept' on every code change it recommends in it's answer, causing VSCode to auto-merge the changes into my code. Couldn't possibly be simpler. Then I scrutinize and test. If anything went wrong I just…

Try doing https://taoofmac.com/space/blog/2025/05/13/2230, you’ll have some fun,

Re: GitHub Copilot Coding Agent

#257

Post by GenshoTikamura »

adamsb6 wrote: post #232
shepherdjerred wrote: post #114

Earlier quoted context omitted.

[flagged]

There's a large group of people that claim that AI tools are no good and I can't tell if they're in some niche where they truly aren't, they don't care to put any effort into learning the tools, or they're simply in denial.

Or simply unwilling to cut their perfectly good legs off and attach those overhyped prostheses that make people so fast and furious at running on the spot

Re: GitHub Copilot Coding Agent

#258

Post by codebolt »

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…

Whatever the true stats for mistakes or blunders are now, remember that this is the worst its ever going to be. And there is no clear ceiling in sight that would prevent it from quickly getting better and better, especially given the current levels of investment.

Re: GitHub Copilot Coding Agent

#259

Post by Cthulhu_ »

literalAardvark wrote: post #98
overfeed wrote: post #76

Earlier quoted context omitted.

> we've merged almost 1,000 pull requests contributed by Copilot I'm curious to know how many Copilot PRs were not merged and/or required human take-overs.

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

I feel the same about automated dependency updates, but if your tests and verifications are good, these become trivial.

Re: GitHub Copilot Coding Agent

#260

Post by Cthulhu_ »

petetnt wrote: post #86
timrogers wrote: post #61

Earlier quoted context omitted.

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…

What about developers who do enjoy writing for example high quality documentation? Do you expect that the status quo will be that most of the documentation will be AI slop and AI itself will just bruteforce itself through the issues? How close are we to the point where the AI could handle "tricky dependency updates", but not being able to handle "most interesting and complex problems"? Who writes the tests that are r…

I'd argue the only way to ensure that is to make sure developers read high quality documentation - and report issues if it's not high quality.

I expect though that most people don't read in that much detail, and AI generated stuff will be 80-90% "good enough", at least the same if not better than someone who doesn't actually like writing documentation.

> What is the job for the developer now? Writing tickets and reviewing low quality PRs? Isn't that the most boring and mundane job in the world?

Isn't that already the case for a lot of software development? If it's boring and mundane, an AI can do it too so you can focus on more difficult or higher level issues.

Of course, the danger is that, just like with other automated PRs like dependency updates, people trust the systems and become flippant about it.

Post reply on HN