Did GitHub Copilot increase my productivity? • Hacker News Board

Re: Did GitHub Copilot increase my productivity?

#211

Post by n4r9 » Mon, May 13, 2024, 11:49 AM UTC

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 have a similar take. As yet I'm unconvinced by claims that using an LLM and correcting the output is faster than just writing the code. What happened to "reading code is harder than writing it"? With an intern or very junior developer you have hope that in a few months/years time they'll be reducing rather than adding to your workload. With an LLM, either you're using it for really rote or boilerplate tasks (fair enough) or you spend so much time looking for subtle errors that it's not worth it. Plus, much less fun than actually crafting something yourself.

Re: Did GitHub Copilot increase my productivity?

#212

Post by anshumankmr » Mon, May 13, 2024, 11:49 AM UTC

Though I have never used CoPIlot myself, I have used Chat GPT for writing emails, adding doc strings, helping with basic boilerplate part like reading a file, generating JSON in a certain structure that the business needs, I can say it has helped but I still don't really trust these models.

Re: Did GitHub Copilot increase my productivity?

#213

Post by jraph » Mon, May 13, 2024, 11:52 AM UTC

> Without it, I find myself getting grumpy a lot more often when I need to write boilerplate code - "Ugh, Copilot would have done it for me!", and now I have to type it all out myself

It seems to me a good IDE generates most of the boilerplate code I would need to write. For Java I use the community edition of IDEA, that's open source, it runs entirely locally and there's no lag. No open source code gets eaten and no forest get burnt.

I spend a vanishingly small time writing boilerplate code. Or so I think. Am I just not noticing it, or is it rare and I work with high quality code?

Re: Did GitHub Copilot increase my productivity?

#214

Post by spaceship__sun » Mon, May 13, 2024, 11:52 AM UTC

anshumankmr wrote: post #212

Though I have never used CoPIlot myself, I have used Chat GPT for writing emails, adding doc strings, helping with basic boilerplate part like reading a file, generating JSON in a certain structure that the business needs, I can say it has helped but I still don't really trust these models.

Average hackernews user.

Re: Did GitHub Copilot increase my productivity?

#215

Post by hippich » Mon, May 13, 2024, 11:55 AM UTC

Copilot certainly increased my productivity. At least in a very specific context - C programming and working on some small subset of llvm internals. I am not very experienced C or C++ programmer, nor I know anything about LLVM API. Plus - copilot is very good at autocompletions. Yes, the code it generates come out often incorrect, but even my low level expertise allows me to spot issues. And even if the code is incorrect - it gives me clues where to dig. Even such a small detail as autocompleting debug printfs is a really big time-saver for me.

I also think that co-pilot vs code integration extension is big part of it. I don't think I would be as productive with chat UI alone. I wonder if there is alternative I can use with local hosted llm that can give me full block autocompletions similar to co-pilot extension. Everything I've seen so far was at best line at a time autocompletion.

Re: Did GitHub Copilot increase my productivity?

#216

Post by thaumasiotes » Mon, May 13, 2024, 11:55 AM UTC

CaptainFever wrote: post #157

YurgenJurgensen wrote: post #153

Earlier quoted context omitted.

Then why not show me? Why is getting AI 'art' advocates to actually post something they think is good and explain why so hard? Where are these talented imaginative people and what are they doing?

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.

Re: Did GitHub Copilot increase my productivity?

#217

Post by neonsunset » Mon, May 13, 2024, 11:58 AM UTC

alrs wrote: post #171

neonsunset wrote: post #168

Earlier quoted context omitted.

It is. Oh, and also, Go managed to screw up even the assembly, inventing portable but actually not dialect that uses ugly bits of AT&T syntax, custom operator precedence and in practice is non-portable, forcing you to mix Go-only mnemonics (which might even collide with opcode names on certain platforms), supported opcodes of target platform, and BYTE literals for opcodes it doesn't support, making a lot of your prel…

It would be great if C# could be discussed as a language on its merits, but Microsoft has been a terrible steward. It's too bad.

So you are saying it's even worse than suing anyone over using the language like a certain Java-related company or laying off people off the core language team like a certain Dart-related company?

Re: Did GitHub Copilot increase my productivity?

#218

Post by naasking » Mon, May 13, 2024, 12:04 PM UTC

marcus_holmes wrote: post #87

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 popul…

> 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.

Even if that were true, reading code is reasonably faster than typing it out and then reading it again to check it.

Re: Did GitHub Copilot increase my productivity?

#219

Post by sumtechguy » Mon, May 13, 2024, 12:12 PM UTC

kaba0 wrote: post #124

noduerme wrote: post #112

Earlier quoted context omitted.

adding an off the shelf ORM layer creates so much more opacity and tech debt than writing queries I don't understand why anyone would willingly put one into their stack. Sure, they're neat although I don't even know if they save time. There's something very satisfying about well-crafted queries. And is it ever really well crafted if you can't tweak them to improve their their execution plan? I've never had a client o…

How do you map rows to objects? How do you insert into/update rows in your databases? These are the basic problems ORMs solve splendidly. They are for OLTP workloads, and have deliberate escape hatches to SQL (or some abstraction over it, like JPQL in java-land). I just fail to see what else would you do, besides implementing a bug-ridden, half-ORM yourself.

That is exactly where ORMs help. The problem is all of the other stuff with it. When most people just need a simple mapper. Not something to build their SQL statements for them (which seems to be why most people pick it).

But that comes to the second problem. Most devs I meet seem to be deathly allergic to SQL. :)

One project I had a dev come to me asking me to look at a bug in the thing. Having never seen that particular ORM before I was able to diagnose what was wrong. Because MS ORMs have the same issues over and over (going back to the 90s). You better read those docs! Because whatever they did in this stack will be in their next one when they abandon it in place 3 years from now.

Re: Did GitHub Copilot increase my productivity?

#220

Post by doubloon » Mon, May 13, 2024, 12:13 PM UTC

The answer is yes for most people. You can type in pseudocode for simple things and out pops something that basically works for a significant number of languages. Its absolutely terrible for really complex problems but most code is not solving complex problems.