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

111–120 of 372 posts

Re: GitHub Copilot Coding Agent

#111

Post by abraham »

qwertox wrote: post #77

In hindsight it was a mistake that Google killed Google Code. Then again, I guess they wouldn't have put enough effort into it to develop into a real GitHub alternative. Now Microsoft sits on a goldmine of source code and has the ability to offer AI integration even to private repositories. I can upload my code into a private repo and discuss it with an AI. The only thing Google can counter with would be to build too…

Gemini has some GitHub integrations

https://developers.google.com/gemini-code-assist/docs/review...

Re: GitHub Copilot Coding Agent

#112

Post by candiddevmike »

qwertox wrote: post #77

In hindsight it was a mistake that Google killed Google Code. Then again, I guess they wouldn't have put enough effort into it to develop into a real GitHub alternative. Now Microsoft sits on a goldmine of source code and has the ability to offer AI integration even to private repositories. I can upload my code into a private repo and discuss it with an AI. The only thing Google can counter with would be to build too…

Google Cloud has a pre-GA product called "Secure Source Manager" that looks like a fork of Gitea: https://cloud.google.com/secure-source-manager/docs/overview

Definitely not Google Code, but better than Cloud Source Repositories.

Re: GitHub Copilot Coding Agent

#113

Post by overfeed »

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?

I'd love to know where you think the starting position of the goal posts was.

Everyone who has used AI coding tools interactively or as agents knows they're unpredictably hit or miss. The old, non-agent Copilot has a dashboard that shows org-wide rejection rates for for paying customers. I'm curious to learn what the equivalent rejection-rate for the agent is for the people who make the thing.

Re: GitHub Copilot Coding Agent

#114

Post by shepherdjerred »

mjr00 wrote: post #99
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…

From talking to colleagues at Microsoft it's a very management-driven push, not developer-driven. Friend on an Azure team had a team member who was nearly put on a PIP because they refused to install the internal AI coding assistant. Every manager has "number of developers using AI" as an OKR, but anecdotally most devs are installing the AI assistant and not using it or using it very occasionally. Allegedly it's pret…

[flagged]

Re: GitHub Copilot Coding Agent

#115

Post by Aurornis »

PretzelPirate wrote: post #33
Scene_Cast2 wrote: post #26

Earlier quoted context omitted.

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.

> Cline very visibly displays the ongoing cost of the task LLMs are now being positioned as "let them work autonomously in the background" which means no one will be watching the cost in real time. Perhaps I can set limits on how much money each task is worth, but very few would estimate that properly.

> LLMs are now being positioned as "let them work autonomously in the background"

The only people who believe this level of AI marketing are the people who haven't yet used the tools.

> which means no one will be watching the cost in real time.

Maybe some day there's an agentic coding tool that goes off into the weeds and runs for days doing meaningless tasks until someone catches it and does a Ctrl-C, but the tools I've used are more likely to stop short of the goal than to continue crunching indefinitely.

Regardless, it seems like a common experience for first-timers to try a light task and then realize they've spent $3, instantly setting expectations for how easy it is to run up a large bill if you're not careful.

Re: GitHub Copilot Coding Agent

#116

Post by grepfru_it »

eterm wrote: post #68
Scene_Cast2 wrote: post #26

Earlier quoted context omitted.

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.

    Hourly_rate / 12 = 5min_rate

    If light_edit_cost

Re: GitHub Copilot Coding Agent

#117

Post by shepherdjerred »

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…

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

Re: GitHub Copilot Coding Agent

#118

Post by shepherdjerred »

eterm wrote: post #68
Scene_Cast2 wrote: post #26

Earlier quoted context omitted.

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.

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

What do you mean?

If I have some task that requires 1000 hours, and I'm able to shave it down to one hour, then I did just "save" 999 hours -- just in the same way that if something costs $5 and I pay $4, I saved $

Re: GitHub Copilot Coding Agent

#119

Post by mjr00 »

shepherdjerred wrote: post #114
mjr00 wrote: post #99

Earlier quoted context omitted.

From talking to colleagues at Microsoft it's a very management-driven push, not developer-driven. Friend on an Azure team had a team member who was nearly put on a PIP because they refused to install the internal AI coding assistant. Every manager has "number of developers using AI" as an OKR, but anecdotally most devs are installing the AI assistant and not using it or using it very occasionally. Allegedly it's pret…

[flagged]

What does this have to do with my comment? Did you mean to reply to someone else?

I don't understand what this has to do with AI adoption at MS (and Google/AWS, while we're at it) being management-driven.

Re: GitHub Copilot Coding Agent

#120

Post by shepherdjerred »

CSMastermind wrote: post #66
lukehoban wrote: post #45

Earlier quoted context omitted.

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.

You can tell the AI not to suppress errors
Post reply on HN