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

81–90 of 326 posts

Re: Did GitHub Copilot increase my productivity?

#81

Post by mucle6 »

Seb-C wrote: post #45

I still haven't found any interest in this wave of AIs for coding, mostly because writing code hasn't been a bottleneck for me since I learned vim and started using it as my only tool. Knowing what to write and how to organize the code is the really difficult part of our job, and I am unable to do this correctly when reviewing stuff written by others (or by an AI). I have been wondering if people are actually using t…

To me copilot feels like a natural extension of vim. Vim is world class for editing code and copilot is incredible at generating code.

Re: Did GitHub Copilot increase my productivity?

#82

Post by BoorishBears »

skydhash wrote: post #71
simonw wrote: post #37

Earlier quoted context omitted.

Absolutely I could have learned more from that particular project if I'd spent more time with it rather than getting the LLM to do the work... but that's why I like it as an example: since it was effectively a distraction (a "side quest") the alternative wasn't learning more, it was not doing it at all (and learning nothing). I'm able to get really great results out of LLMs because I have 20+ years of experience help…

> I'm able to get really great results out of LLMs because I have 20+ years of experience helping me know what questions to ask of them. While a direct answer is nice, I like an iterative/explorative process because of all the things I pick up alongside it. An example is when I was working on an epub reader for macOS (side project). I wanted to a native layout engine instead of a webview and I decided to go with muPD…

You're talking right past them though: you were working on a side quest you had interest and bandwidth to iterate on.

I agree with the parent comment, my pipeline is already saturated with side quests, I'm already iterating on a bunch of random fun work, and side-project work and work work. So often times the most "LLM-heavy" projects of mine are things I straight up would not do if I didn't have something to get the ball rolling other than more of my own free time which is already in short supply.

Hopping from direct answer to direct answer isn't where I find wonder/fun in programming anyways, but sometimes you don't have bandwidth for the side quest to be fun or wonderous.

Re: Did GitHub Copilot increase my productivity?

#83

Post by mucle6 »

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…

I am so confused. When I write code, I think "Okay I want to write a for loop that does xyz." How is it hard to know if copilot did or didn't do what you wanted?

Re: Did GitHub Copilot increase my productivity?

#84

Post by marcus_holmes »

dudus wrote: post #74
mlinhares wrote: post #49

Earlier quoted context omitted.

So rails scaffold from 20 years ago but with a chance of hallucinations?

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).

Re: Did GitHub Copilot increase my productivity?

#85

Post by fendy3002 »

frizlab wrote: post #28
fendy3002 wrote: post #15

Earlier quoted context omitted.

And for those who say that it doesn't speed up development, then maybe they're right, because the main benefit isn't at speed. It reduce the devs mental / cognitive load and pass it to the ai instead, we just need to check and review the result. If it doesn't monumentally increase the speed, it helps devs to stay productive longer

Reviewing code is famously harder than writing it. I don’t see how it’s a gain to have to review more code than to write.

In some cases where I often use it I find it easy. Usually I give an ORM class and ask it to parse to mysql / postgres create table. Tedious tasks and easy to review.

Another time I asked to generate a code to listen to SMTP server using a library, and again it's easier to review because I was not familiar with the library. From that I can make my own adjustment.

Re: Did GitHub Copilot increase my productivity?

#86

Post by serpix »

mucle6 wrote: post #83
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…

I am so confused. When I write code, I think "Okay I want to write a for loop that does xyz." How is it hard to know if copilot did or didn't do what you wanted?

This is how I've used it: "I want to write a function that reduces a map of customer data to a list of their phone numbers from their primary addresses only or contact address if there is no primary address"

and then you look at the resulting flatmap, filter, reduce blob of AI generated code and figure out if what it does is correct for about a minute.

Re: Did GitHub Copilot increase my productivity?

#87

Post by marcus_holmes »

Years ago, over a decade ago now, I was a .Net developer. Microsoft introduced Entity Framework, their new way of handling data in .Net applications. Promises made, promises believed, we all used it. I was especially glad of Lazy Loading, where I didn't have to load data from the database into my memory structures; the system would do that automatically. I could write my code as if all my memory structures were populated and not worry about it. Except, it didn't work consistently. Every now and again a memory structure would not be populated, for no apparent reason. Digging deep into technet, I found a small note saying "if this happens, then you can check whether the data has been loaded by checking the value of this flag and manually loading it if necessary" [0]. So, in other words, I have to manually load all my data because I can't trust EF to do it for me. [1]

Long analogy short, this is where I think AI for coding is now. It gets things wrong enough that I have to manually check everything it does and correct it, to the point where I might as well just do it myself in the first place. This might not always be the case, but that's where I feel it is right now.

[0] Entity Framework has moved on a lot since then, and apparently now can be trusted to lazily load data. I don't know because...

[1] I spat the dummy, replaced Windows with Linux, and started learning Go. Which does exactly what it says it does, with no magic. Exactly what I needed, and I still love Go for this.

Re: Did GitHub Copilot increase my productivity?

#88

Post by tymscar »

simonw wrote: post #8
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…

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”?

Re: Did GitHub Copilot increase my productivity?

#89

Post by eru »

skydhash wrote: post #68
eru wrote: post #60

Earlier quoted context omitted.

Yes, I often find that copilot is pretty good at picking up on the pattern of refactorings that I am doing. Especially those that are a bit tedious and almost mechanical, but not quite mechanical enough to do with a simple search-and-replace.

Vim and text motions should do the trick.

Totally depends on what kind of refactoring you want to do; and how well vim's commands map to your language's syntax, too. (Or whether your vim has special support for your language's syntax.)

Re: Did GitHub Copilot increase my productivity?

#90

Post by thefaux »

simonw wrote: post #8
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…

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 creating a false dichotomy. Very few people are saying there are no benefits, but many have reasonable concerns both about the current efficacy of these tools as well as the expectation of continued exponential growth which is driving much of the current hype.

What if we have already passed the inflection point where the exponential growth transitions to an s-curve? That would mean that this technology on its own would only get marginally better than is today. Maybe 2, 4 or even 10x better than it is today, but not 100x or 1000x. To break those barriers, we would need further innovations beyond just throwing more gpus and training data at the problem.

I personally am short on LLMs because I believe it is much more likely that we have already crossed the inflection point or will soon. Again, they are impressive but ultimately I think that LLMs will be at best a footnote in history if they are even remembered at all in a few hundred years. But of course I could be wrong.

Post reply on HN