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

221–230 of 372 posts

Re: GitHub Copilot Coding Agent

#221

Post by sethammons »

dontlikeyoueith wrote: post #16
tmpz22 wrote: post #10

Earlier quoted context omitted.

I’m always hesitant to listen to the line coders on projects because they’re getting a heavy dose of the internal hype every day. I’d love for this to blow past cursor. Will definitely tune in to see it.

>I’m always hesitant to listen to the line coders on projects because they’re getting a heavy dose of the internal hype every day. I'm senior enough that I get to frequently see the gap between what my dev team thinks of our work and what actual customers think. As a result, I no longer care at all what developers (including myself on my own projects) think about the quality of the thing they've built.

These do not need to be mutually exclusive. Define the quality of the software in terms of customer experience and give developers ownership to improve those markers. You can think service level objectives.

In many cases, this means pushing for more stable deployments which requires other quality improvements.

Re: GitHub Copilot Coding Agent

#222

Post by s-lambert »

timrogers wrote: post #173
leptons wrote: post #167

Earlier quoted context omitted.

> 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. I get paid for the mundane, boring, annoying tasks, and I really like getting paid .

But would you rather get paid to spend your time doing the interesting and enjoying work, or the mundane and boring stuff? ;) My hope is that agents like Copilot can help us burn down the tedious stuff and make more time for the big value adds.

But working on interesting things is mentally taxing while the tedious tasks aren't, I can't always work at full bore so having some tedium can be a relief.

Re: GitHub Copilot Coding Agent

#223

Post by akmarinov »

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 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, while keeping performance and security - code structure, quality and readability don’t matter one bit.

Customers don’t care about code quality and the only reason businesses used to care is to make it less money consuming to build and ship new things, so they can make more money.

Re: GitHub Copilot Coding Agent

#224

Post by beefnugs »

DeepYogurt wrote: post #75
twodave wrote: post #23

Earlier quoted context omitted.

I feel like I saw a quote recently that said 20-30% of MS code is generated in some way. [0] In any case, I think this is the best use case for AI in programming—as a force multiplier for the developer. It’s for the best benefit of both AI and humanity for AI to avoid diminishing the creativity, agency and critical thinking skills of its human operators. AI should be task oriented, but high level decision-making and…

> I feel like I saw a quote recently that said 20-30% of MS code is generated in some way. [0] Similar to google. MS now requires devs to use ai

So demanding all employees use it... results in less than 30% compliance. That does tell me a lot

Re: GitHub Copilot Coding Agent

#225

Post by OutOfHere »

timrogers wrote: post #182
OutOfHere wrote: post #64

Which model does it use? Will this let me select which model to use? I have seen a big difference in the type of code that different models produce, although their prompts may be to blame/credit in part.

At the moment, we're using Claude 3.7 Sonnet - but we're keeping our options open to experiment with other models and potentially bring in a model picker. (Source: I'm on the product team for Copilot coding agent.)

Do you at least control the prompt?

In my experience using Claude Sonnet 3.7 in GitHub Copilot extension in VSCode, the model produced hideously verbose code, completely unnecessary stuff. GPT-4.1 was a breath of fresh air.

Re: GitHub Copilot Coding Agent

#226

Post by theappsecguy »

akmarinov wrote: post #223
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 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…

Wild take. Let’s just hand over the keys to LLMs I suppose, the fancy next token predictor is the capitan now.

Re: GitHub Copilot Coding Agent

#227

Post by BeetleB »

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…

Have you tried Gemini 2.5? It's cheaper and scores higher on the Aider leaderboard.

Re: GitHub Copilot Coding Agent

#228

Post by spicypete »

grepfru_it wrote: post #116
eterm wrote: post #68

Earlier quoted context omitted.

> 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

(from a companies perspective, this is true). As a developer, you may not be paid by the task -- If I finish something early, I start work on the next thing.

Re: GitHub Copilot Coding Agent

#229

Post by peterson_lock »

caseysoftware wrote: post #206

So, fun thing.. LinkedIn doesn't use Copilot. I recently created an course for LinkedIn Learning using generative AI for creating SDKs[0]. When I was onsite with them to record it, I found my Github Copilot calls kept failing.. with a network error. Wha? Turns out that LinkedIn doesn't allow people onsite to to Copilot so I had to put my Mifi in the window and connect to that to do my work. It's wild. Btw, I love wor…

> LinkedIn doesn't use Copilot

They definitely use it for full-time SWEs

Source: I work there

Re: GitHub Copilot Coding Agent

#230

Post by porridgeraisin »

BeetleB wrote: post #74
nodja wrote: post #37

I wish they optimized things before adding more crap that will slow things down even more. The only thing that's fast with copilot is the autocomplete, it sometimes takes several minutes to make edits on a 100 line file regardless of the model I pick (some are faster than others). If these models had a close to 100% hit rate this would be somewhat fine, but going back and forth with something that takes this long is…

Several minutes? Something is seriously wrong. For most models, it takes seconds.

It takes minutes for me too sometimes.

Cursor is quicker, I guess it's a response parsing thing - when they make the decision to show it in the UI.

Post reply on HN