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

351–360 of 372 posts

Re: GitHub Copilot Coding Agent

#351

Post by shwouchk »

sensanaty wrote: post #342
th0ma5 wrote: post #200

Earlier quoted context omitted.

No, not at all. Why do people keep saying shit like these thought terminating sentences. Try to see the glass of Kool Aid please. People are trying to understand how to communicate important valuable things about failure states and you're advocating ignorance.

Because the marketing started with "This is literally the singularity and will take over everything and everyone's jobs". Then people realized that was BS, so the marketing moved on to "This will enhance everyone's jobs, as a companion that will help everyone". People also realized that was pure BS. A few more marketing rebrands later and we're at the current situation where we try to equate it to the lowest possible…

for better or worse, this is literally the singularity. this thing will eat the world.

Re: GitHub Copilot Coding Agent

#352

Post by kookamamie »

xur17 wrote: post #315
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).

Yes, so it seems.

Re: GitHub Copilot Coding Agent

#353

Post by quantadev »

rcarmo wrote: post #256
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,

I've come to the same conclusions mentioned in most of that and done most of that already. I was an early-adopter of LLM tech, and have my own coding agent system, written in python. Soon I'm about to port those tools over to MCP so that I can just use VSCode for most everything, and never even need my Gradio Chatbot that I wrote to learn how to write tools, and use tools.

My favorite tool that I've written is one that simply lets me specify named blocks by name, in a prompt, and AI figures out how to use the tool to read each block. A named block is defined like:

# block_begin MyBlock ...lines of code # block_end

So I can just embed those blocks around the code rather change pasting into prompts.

Re: GitHub Copilot Coding Agent

#354

Post by gen220 »

rcarmo wrote: post #251
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…

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

I like this a lot! My root README ends up looking a lot like your SPEC.md, and I also have a file that’s pretty similar to your TODO.md.

My experience agrees that separating the README and the TODO is super helpful for managing context.

Re: GitHub Copilot Coding Agent

#355

Post by quantadev »

SkyBelow wrote: post #349
quantadev wrote: post #197

Earlier quoted context omitted.

I assumed I was using 'Agent mode' but now that you mentioned it, I checked and you're right I've been in 'Ask mode' instead. oops. So thanks for the tip! I'm looking forward to seeing how Agent Mode is better. Copilot has been such a great experience so far I haven't tried to keep up with every little new feature they add, and I've fallen behind.

I find agent mode much more powerful as it can search your code base for further reference and even has access to other systems (I haven't seen exactly what is the other level of access, I'm guessing it isn't full access to the web but it can access certain only info repositories). I do find it sometime a little over eager to do instead of explain, so Ask mode is still useful when you want explanations. It also appea…

Yeah in Ask mode, it shows me the code it's proposing, and explains it, and I have to click an icon to get it to merge the change into my code tentatively and then click "Keep" to make it actually merge into the code permanently. I kind of like that workflow a lot, but I guess you're saying Agent Mode just slams the changes into the code. I may or may not like that. Often I pick only, parts of what it's done. Thanks for the tips.

Re: GitHub Copilot Coding Agent

#356

Post by akmarinov »

FeepingCreature wrote: post #287
akmarinov wrote: post #223

Earlier quoted context omitted.

> I noticed that LLMs need a very heavy hand in guiding the architecture, otherwise they'll add architectural tech debt. One easy example is that I noticed them breaking abstractions That doesn’t matter anymore when you’re vibe coding it. No human is going to look at it anyway. It can all be if/else on one line in one file. If it works and if the LLMs can work at, iterate and implement new business requirements, whil…

LLMs need a very heavy hand in guiding the architecture because otherwise they'll code it in a way that even they can't maintain or expand.

Hook up something like Taskmaster or Shrimp, so that they can document as they go along and they can retrieve relevant context when they overflow their context to avoid this issue.

Then as the context window increases, it’s less and less of an issue

Re: GitHub Copilot Coding Agent

#357

Post by dyauspitr »

Scene_Cast2 wrote: post #198
dyauspitr wrote: post #166

Earlier quoted context omitted.

I don’t get it? Isn’t it just a monthly fixed subscription.

Nope - I use a-la-carte pricing (through openrouter). I much prefer it over a subscription, as there are zero limits, I pay only for what I use, and there is much less of a walled garden (I can easily switch between Anthropic, Google, etc).

I’m running o3 dozens of times a day all for the subscription price of $20. Surely this is way more cost effective.

Re: GitHub Copilot Coding Agent

#358

Post by Xunjin »

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…

TBF, you are more than biased to conclude this, I definitely take your opinion with an whole bottle of salt.

Without data, a comprehensive study and peers review, it's a hell no. Would GitHub willing to be at academic scrutiny to prove it?

Re: GitHub Copilot Coding Agent

#359

Post by no_wizard »

Cthulhu_ wrote: post #259
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 feel the same about automated dependency updates, but if your tests and verifications are good, these become trivial.

Strong automated tests and verifications seem to be nearly as rare as unicorns, at least if you take most of developers feelings on this.

It seems places don't prioritize it, so you don't see it very often. Some developers are outright dismissive of the practice.

Unfortunately, AI won't seemingly help with that

Re: GitHub Copilot Coding Agent

#360

Post by joejoo »

sensanaty wrote: post #340
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 (115733) would make me quit after a week if we were to implement this crap at my job and someone forced me to babysit an AI in its PRs in this fashion. The others are also rough. A wall of noise that tells you nothing of any substance but with an authoritative tone as if what it's doing is objective and truthful - Immediately followed by: - The 8 actual lines of code (discounting the tests & boilerplate…

[dead]
Post reply on HN