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

271–280 of 326 posts

Re: Did GitHub Copilot increase my productivity?

#271

Post by echelon »

thaumasiotes wrote: post #216
CaptainFever wrote: post #157

Earlier quoted context omitted.

Air Head by shy kids https://www.youtube.com/watch?v=G4wJ4WeJrz4 You also don't see the everyday people using it to generate pictures about their own experiences and lives, using it to populate their DnD worlds, their personal unpublishable fanfics, etc.

The balloon is a different shape from shot to shot, and - much worse - in a few of the shots it appears to be hovering in front of the rest of the image rather than occupying the space where Air Head's neck should be. Is it better than I could do? Yep. Is it failing a bar that any human would pass? Yep. Is it better than relevant artists? Nope. But it is cheaper.

Literally everyone in this space is working on controllability. The cherry picked issue you cited has hundreds of the best minds tackling it as we speak.

This is the worst it will ever look. It's only going to improve from here.

Compare that to the early days of silent film. The profess with Gen AI is astounding.

We're going to have Disney/Pixar and Scorsese outputs by the end of the decade. (I'd be willing to wager even sooner than that.)

Re: Did GitHub Copilot increase my productivity?

#272

Post by datavirtue »

devjab wrote: post #164
klauserc wrote: post #148

I find GitHub Copilot close to useless for production code. The worst, most obscure bugs I've had to debug in the last year were all in Copilot-written code. It _looks_ plausible, but it makes extremely subtle mistakes. Occasionally, you have repetitive sections of code where it can copy&adapt lines from the context, but that's about it. It's a different story for test code. Test code is often formulaic and "standard…

I think automated tests are the one area that LLMs will truly improve productivity (and overall code quality). It’ll likely also lead to a lot of tests that actually tests nothing, but as a whole, it’ll hopefully be capable of both generating and updating tests if you give it some good inputs to do it on. Documentation is another area where I have high hopes. In the ideal world people update it as they change things.…

A test that tests nothing is redundant and therefore is not a test. I have seen people make claims about "useless tests" when they are not able to reason about the coverage. You should be using a tool to gauge test coverage. Tests should be proving accuracy and precision. It's easy to conflate those or lose sight of one.

Re: Did GitHub Copilot increase my productivity?

#273

Post by devjab »

DangitBobby wrote: post #261
devjab wrote: post #154

Earlier quoted context omitted.

You always have to worry about your model changes if you run at any sort of scale. Some ORMs will get it right most of the time, but the few times they don’t will really bite you in the ass down the line. Especially with the more “magical” ORMs like EF where you might not necessarily know how it build your tables unless you specifically designed them yourself. This is where migrations also become sort of annoying. Be…

> And what is the plus side of having a code-first DB really? You can fairly easily store those “alter table” changes as you go along and have full availability of history in a very readable way that anyone, including people not using C#, Java, Python. The benefits should be obvious if you've used ORMs. They are an object that represents your database data in code rather than in a table where you can't touch it. If y…

The only area of development where ORMs haven’t been the cause for at least some trouble in my career has been with relatively small and completely decoupled services. Even here I’ve had to replace countless ORMs with more efficient approaches as the service eventually needed to be build with C/C++. That being said, I don’t think any of these should have been build without the ORM. The rewrite would have been almost as much of a hassle if there hadn’t been an ORM after all.

I’m not really against ORMs as such. I’m not a fan of code-first databases for anything serious, but as far as CRUD operations goes I don’t see why you wouldn’t use an ORM until it fails you, which it won’t in most cases, and in those cases where it does… well similar to what I said earlier you just wouldn’t have build it to scale from the beginning anyway, and if you had and it turned out it didn’t need to scale then you probably wasted a lot of developer resources to do so.

Re: Did GitHub Copilot increase my productivity?

#274

Post by fzeroracer »

DrSiemer wrote: post #132
erhaetherth wrote: post #108

Earlier quoted context omitted.

I was trying to fetch key-value pairs out of a database using PHP+PDO the other day and I knew there was a nice easy to do it but I couldn't remember how. Something about fetchAll, maybe PDO::FETCH_GROUP|PDO::FETCH_COLUMN.... what was it? So I asked a couple LLMs. They wrote out loops for me to format the data how I wanted. I could have copy-and-pasted that in and it would probably have worked. But I felt there was s…

Strong disagree. I have learned so many new things since I started using LLM's. Some of them I'm actually embarrassed to admit, because I should have known about them a decade ago. If you work in a small company and you are the most experienced developer, you don't often get feedback on how you can improve things. The trick is, quite simply: just ask. I regularly dump some code I wrote in a language model and then as…

This is precisely the wrong way to engage with LLMs. If you are asking it 'what can be done better', it'll spit out something. That something isn't necessarily better or not because it has no concept of 'better' or 'worse'.

Re: Did GitHub Copilot increase my productivity?

#275

Post by 999900000999 »

Chat GPT and friends are best when you tell it to write code from scratch, even then it's only good for straight forward tasks.

Give it existing code to work with, particularly a larger code base and things get weird.

Still, I love it for hacking out small prototypes. If you don't really care about performance or best practice, it's ok.

Re: Did GitHub Copilot increase my productivity?

#276

Post by b33j0r »

eesmith wrote: post #118
b33j0r wrote: post #39

I disable it when I actually need to recall what I know. It’s like a phone number. If you never dial your mom anymore, you will forget it.

Or like GPS? While GPS gets me where I want to go, I find that using a map or no map at all gives me a better sense of place, so I need less time to get to the point where I don't need a GPS to get around.

100%. Retain the things that you need, don’t memorize wikipedia. See your landscape.

Re: Did GitHub Copilot increase my productivity?

#277

Post by leptons »

collyw wrote: post #192
leptons wrote: post #50

Earlier quoted context omitted.

I only use Copilot for my day job, because they paid for it. When I'm coding my personal projects on nights and weekends I find myself missing Copilot and I'm contemplating paying for it myself. I don't really trust it for everything, but sometimes it surprises me with how much it gets right. I just can't justify paying $19/month personally for the "Business" plan so they don't use my proprietary code to train their…

I used ChatGPT 4 while doing some freelance projects, and considering the time it has saved me, it's easily worth the 20 bucks a month. It is by no means perfect, but I look at it more like a super powered stack overflow.

About all I really use Copilot for is auto-completing console.log statements. That's most of what I like it to do. I don't need an AI to write code for me. I already know the code I'm writing better than the AI does. Sometimes the AI guesses what I'm about to write and fills it in, and sometimes I let it, but I don't trust based on my experience with it, and then I have to read a paragraphs length of code to make sure it's right before I allow it, and it's usually wrong so I've just wasted some time thanks to the AI. It gets it wrong more often than it gets anything complicated right, and often suggests buggy code. I can't really see paying for that for myself. I don't think auto-completing console.log statements is worth $20/month.

Re: Did GitHub Copilot increase my productivity?

#278

Post by dudus »

LtWorf wrote: post #155
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.

What about the problem of needless pollution?

I thought we had moved on from cryptocurrencies

Re: Did GitHub Copilot increase my productivity?

#279

Post by anguspmitchell »

jpollock wrote: post #41

I enjoy working with interns, you can see them learn and they are always making new mistakes. I get a return on the effort of training them. They might even convert into full time employees and take some of my workload. I don't get that feeling from the LLMs. They have about the same skill level of an intern, but they don't _learn_. I can't offload any work to them, and they take the same level of effort to manage. I…

I think the intern analogy is right.

The problem is that there’s always a communication cost to outsourcing something. And you can’t outsource a whole project to an LLM, like a human intern. You’re just outsourcing one micro-, sub-task after another. To use the human analogy, it’s more like you’re standing over their shoulder and telling them what function to write, one after the other. And they’re SUPER fast with small, pure functions, but they get confused with anything else.

Is that a faster way to program?

Maybe? If you can fluidly decompose things into small functions in your head and the problem can be solved that way?

I don’t know though, I find myself using chatGPT for bigger meta questions much more frequently than the Copilot autocomplete

Re: Did GitHub Copilot increase my productivity?

#280

Post by freedomben »

cultofmetatron wrote: post #223
arrowsmith wrote: post #133

Earlier quoted context omitted.

I wouldn't have believed you until I moved from ActiveRecord (Rails's ORM) to Ecto (Elixir/Phoenix's data mapping library which is decidedly not an ORM.) It's a million times better and I'm never going back.

same, I wish more libraries would go the ecto design route. my ecto queries map pretty close to 1:1 with the sql counterpart. no guessing what the output is going to look like. I spend my time debugging the query and not trying to get the orm to output he query I want.

Yes, same experience here. I felt (and still feel) that ActiveRecord is one of if not the best ORMs out there, but it was always a source of debugging and performance optimizations/pain, and the trick was basically taking hand-written SQL and trying to get ActiveRecord to generate that. After briefly moving to node.js full time I actually got very anti-ORM, although query building libraries all sucked too which left me unsure of what the best approach is.

Then I learned Ecto/Phoenix and this is truly the best way. Ecto is so close and translateable to raw SQL that there's little to no friction added by it, but it handles all the stuff you don't want to have to do by hand (like query building, parameterization, etc). Ecto is a real breath of fresh air and I find myself writing quick scripts that hit a database in Elixir just so I can use Ecto! I also love how easy Ecto makes it to model database tables that were originally defined by another language/framework or even by hand. Trying to do that with ActiveRecord or another ORM is usually a recipe for extreme pain, but with Ecto it's so easy.

Post reply on HN