Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Did GitHub Copilot increase my productivity?

trace.yshui.dev

Post reply on HN
Print view View original

91–100 of 326 posts

Re: Did GitHub Copilot increase my productivity?

#91

Post by noobermin »

muglug wrote: post #29

GitHub touts a 55% improvement in coding speed based on a study conducted in-house that tested the participants’ ability to paste a pre-written prompt and then check the output: https://github.blog/2022-09-07-research-quantifying-github-c... The effectiveness of a Copilot-like tool trialed at FB showed that 8% of code contributed by participants was sourced from suggestions, but the latter study made no promise about…

So I am a scientist and I've generally resisted using llms for my work. My general critique reading others' experience is this sounds like what is needed is better abstractions if all it helps people with is doing boilerplate that needs to be checked. Also no need for "better abstractions" to be some ethereal thing, this just means better standardised libraries and frameworks. May be if the word "abstractions" sounds too bespoke may be what is needed is better tools and tooling.

The standardised bit seems more difficult than it should be as it's essentially a social problem with development in general, but that also is a problen AI does not address, it's merely a bandaid over the problem.

Re: Did GitHub Copilot increase my productivity?

#92

Post by noobermin »

AnarchismIsCool wrote: post #2

Local maxima go BRRRRRRR AI will get there eventually, but this current paradigm seems increasingly only useful for spam and shitty clip art. Even so, everyone is throwing absurd amounts of investment capital at it in the hopes that something useful will happen. It's a pretty clear depiction of the investor class being so detached from the technical reality of what they're investing in that they just sit around light…

People are either misusing this meme or it makes no sense.

Re: Did GitHub Copilot increase my productivity?

#93

Post by noobermin »

matrix87 wrote: post #23

I don't really get the value proposition, for every second you spend writing something you spend another 10 verifying that it was done properly. Speeding up the process of writing is sort of a waste because of Amdahl's law How does copilot et al. speed up verification and review? For example, a C program is harder to verify than a Go program doing the same thing. Suppose you use it to verify something in an enterpris…

Beware the hype and those pushing the hype, especially when certain entities have wares to sell. While you should keep an open mind within reason, trust your experience and basic reasoning before you throw everything out to buy the snakeoil.

Re: Did GitHub Copilot increase my productivity?

#94

Post by ToValueFunfetti »

tymscar wrote: post #88
simonw wrote: post #8

Earlier quoted context omitted.

I've been finding this stuff genuinely useful for two years now, across Copilot and ChatGPT and Claude 3 Opus and similar tools. Either I'm a dimwit, easily conned by hype and shiny tools to the point that I can imagine benefits for two years that simply aren't there... or there's something to them.

You are clearly not a dimwit, and you don’t only have way more experience than most people here, you also have some amazing projects under your belt. However I can’t help but notice that the vast majority of blogposts, talks, tweets, and basically everything else you do now is around LLMs. Do you not think that’s indicative of this being “hyped” and “shiny tools”?

If hype just means people are excited about it and talking about it, it should be a positive signal about the merit of the thing. I think people get the wrong idea by measuring P(X is good | people are excited about X) and finding it to be low. But P(X is good | people are not excited about X) is vastly lower, and 'hype' as here used is not really discrediting.

Re: Did GitHub Copilot increase my productivity?

#95

Post by anonzzzies »

azinman2 wrote: post #31
anonzzzies wrote: post #27

Earlier quoted context omitted.

Correct, but that was also the point; all these ‘consultants’ are senior programmers. Nothing is magically done; they use the ai to do the work they were mostly doing before with more people/themselves without ai; now they just focus more on business side. Higher pay and harder to replace (for now). My company does the same but in a niche; our specific tooling is easier to automate (which we did/are still doing) and…

> he saw his EU clients cancelling all his contracts because his people could be replaced by openai But this is what I want to know. They thought they could replace the ppl in the first place.

Ah, but those were not consultants or maybe you didn’t mean that. Most of these clients hired people to augment their in house EU teams so they don’t need to hire more programmers locally; after 6-12 months of using copilot/gpt they found out they now could do that work in house with only the in house people in the same time. So they let go of the outsourced team members. I see this happening everywhere. It’s mostly the people that do the ‘light’ work; crud, integrations, frontend, data cleaning that are getting removed; this is a massive portion work wise, but simple, repetitive and boring. Things like business logic, workflows, data science, ml, performance and devops are done in house or still outsourced.

Re: Did GitHub Copilot increase my productivity?

#96

Post by thiht »

I’ve configured Copilot to generate suggestions only when I explicitly use a keyboard shortcut and it’s been a game changer for me. I’ve developed a good intuition of what it’s good at and now I much prefer invoking it manually. When it automatically suggests garbage on every keypress, it gets frustrating pretty fast.

Re: Did GitHub Copilot increase my productivity?

#97

Post by perfmode »

marcus_holmes wrote: post #84
dudus wrote: post #74

Earlier quoted context omitted.

It's very easy to find multiple solutions to one problem. The power of LLM is that it's one solution to many problems.

But is it actually a solution to any of them? The "chance of hallucinations" is the tricky bit - if I have to manually check everything it does in case it's hallucinating, then it's not actually a solution. It's not saving me time (as TFA says).

while you’re in doubt, i’ll be speeding out

Re: Did GitHub Copilot increase my productivity?

#99

Post by esskay »

Anecdotally I can say it's improved my productivity. Mainly because it's just a slightly better autocomplete than PHPStorm/Jetbrains IDE provides. Although they are now pushing their own AI tools for an extra fee pretty heavily but unlikely to pay for it given copilot pricing is pretty competitive.

There are occasions where I'm just not in the mood to work something complex out so sticking a temporary comment in telling it what to do can sometimes yield a good enough result, all be it with some occasional minor tweaking.

Where it's really shined is with repetitive tasks. It's nothing close to perfect but it's certainly a welcomed little helper even if it does get things wrong sometimes.

In terms of the original question, I think its the cognative mental load thats being helped here more than anything, not having to waste brain power on the mundane bits is the big selling point for me.

Re: Did GitHub Copilot increase my productivity?

#100

Post by ghaff »

echelon wrote: post #22
AnarchismIsCool wrote: post #2

Local maxima go BRRRRRRR AI will get there eventually, but this current paradigm seems increasingly only useful for spam and shitty clip art. Even so, everyone is throwing absurd amounts of investment capital at it in the hopes that something useful will happen. It's a pretty clear depiction of the investor class being so detached from the technical reality of what they're investing in that they just sit around light…

> shitty clip art AI art is better than most humans, including most artists. You can take the outputs and immediately turn them into animation. Suddenly I, as a single individual, can easily make film content without figuring out set and lighting logistics or roping in dozens of people. This stuff is magic.

I was somewhat with you through the first sentence then it got a bit breathless. As someone with some graphic design experience but who isn’t very good and can’t really draw, I used Photoshop and it’s genAI capability recently to put together a book cover for an ebook.

Would it win any awards? I’m pretty sure not but it’s more than adequate for its purpose and is almost certainly better than anything I could have come up with even if I used some CC artwork.

ADDED: I also had something of a vision for what I was looking for and (I think) enough of an eye to fiddle with things and get to the point where I went "This isn't half bad."

Post reply on HN