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

191–200 of 372 posts

Re: GitHub Copilot Coding Agent

#191

Post by ayrtondesozzla »

doug_durham wrote: post #96
petetnt wrote: post #86

Earlier quoted context omitted.

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…

If find your comment "AI Slop" in reference to technical documentation to strange. It isn't a choice between finely crafted prose versus banal text. It's documentation that exists versus documentation that doesn't exist. Or documentation that is hopelessly out of date. In my experience LLMs do a wonderful job in translating from code to documentation. It even does a good job inferring the reason for design decisions.…

> If I want well written prose I'll read literature.

Actually if you want well-written prose you'll read AI slop there too. I saw people comparing their "vibe writing" workflows for their "books" on here the other day. Nothing is to be spared, apparently

Re: GitHub Copilot Coding Agent

#192

Post by malfist »

dankwizard wrote: post #189
bionhoward wrote: post #147

Major scam alert, they are training on your code in private repos if you use this You can tell because they advertise “Pro” and “Pro+” but then the FAQ reads, > Does GitHub use Copilot Business or Enterprise data to train GitHub’s model? > No. GitHub does not use either Copilot Business or Enterprise data to train its models. Aka, even paid individuals plans are getting brain raped

If you're programming on Windows, your screen is being screenshotted every few seconds anyway. If you don't think OCR isn't analysing everything resembling a letter on your screen boy do I have some news for you.

Windows recall is not installed by default

Re: GitHub Copilot Coding Agent

#193

Post by taurath »

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…

> In the repo where we're building the agent, the agent itself is actually the #5 contributor - so we really are using Copilot coding agent to build Copilot coding agent ;)

Thats a fun stat! Are humans in the #1-4 slots? Its hard to know what processes are automated (300 repos sounds like a lot of repos!).

Thank you for sharing the numbers you can. Every time a product launch is announced, I feel like its a gleeful announcement of a decrease of my usefulness. I've got imposter syndrome enough, perhaps Microsoft might want to speak to the developer community and let us know what they see happening? Right now its mostly the pink slips that are doing the speaking.

Re: GitHub Copilot Coding Agent

#194

Post by n2d4 »

tines wrote: post #145
n2d4 wrote: post #105

Earlier quoted context omitted.

It's not survivorship bias. Survivorship bias would be if you made any conclusions from the 1000 merged PRs (eg. "90% of all merged PRs did not get reverted"). But simply stating the number of PRs is not that.

As with all good marketing, the conclusions omitted and implied, no?

The implied conclusion ("Copilot made 1000 changes to the codebase") is also not survivorship bias.

By that logic, literally every statement would be survivorship bias.

Re: GitHub Copilot Coding Agent

#195

Post by latentsea »

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…

> In the repo where we're building the agent, the agent itself is actually the #5 contributor - so we really are using Copilot coding agent to build Copilot coding agent ;)

Ah yes, the takeoff.

Re: GitHub Copilot Coding Agent

#196

Post by cmrdporcupine »

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.

So like the typical junior developer, then.

Re: GitHub Copilot Coding Agent

#197

Post by quantadev »

SkyBelow wrote: post #121
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…

Have you tried the agent mode instead of the ask mode? With just a bit more prompting, it does a pretty good job of finding the files it needs to use on its own. Then again, I've only used it in smaller projects so larger ones might need more manual guidance.

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.

Re: GitHub Copilot Coding Agent

#198

Post by Scene_Cast2 »

dyauspitr wrote: post #166
Scene_Cast2 wrote: post #8

I tried doing some vibe coding on a greenfield project (using gemini 2.5 pro + cline). On one hand - super impressive, a major productivity booster (even compared to using a non-integrated LLM chat interface). 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 (putting things where they do…

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).

Re: GitHub Copilot Coding Agent

#199

Post by shepherdjerred »

ipaddr wrote: post #161
shepherdjerred wrote: post #117

Earlier quoted context omitted.

$15 in an evening sounds like a great deal when you consider the cost of highly-paid software engineers

The money won't be flowing forever. This will cost you $6,000 a year.

A new grad at a FANG costs ~$200k-$250k a year after benefits

Re: GitHub Copilot Coding Agent

#200

Post by th0ma5 »

cmrdporcupine wrote: post #196
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.

So like the typical junior developer, then.

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.
Post reply on HN