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

321–326 of 326 posts

Re: Did GitHub Copilot increase my productivity?

#321

Post by freedomben »

randomdata wrote: post #297
freedomben wrote: post #281

Earlier quoted context omitted.

I agree with you, but I do think there's a little fuzziness between full-blown ORM and a tuple-populating query builder in some cases. For example Ecto, which can have understanding of the table schema and populate a struct with the data. It's just a struct though, not an object. There's no functions or methods on it, it's basically just a tuple with a little more organization.

> It's just a struct though, not an object. There's no functions or methods on it Object-relational mapping was originally coined in the Smalltalk world, so objects were in front of mind, but it was really about type conversion. I am not sure that functions or methods are significant. It may be reasonable to say that a struct is an object, for all intents and purposes. A pendant might say that what flimsy definition…

Thanks for the thoughts, that's a good point. It certainly makes sense that the "object" merely needs typed properties to qualify.

Re: Did GitHub Copilot increase my productivity?

#322

Post by hippich »

bogwog wrote: post #240
hippich wrote: post #215

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 incor…

> 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. I'm not sure what you're working on, but as someone dependent on LLVM-based tools, reading this is kind of terrifying. I'm sure your intentions are good, but I hope you're at least making it clear that you're heavily reliant on the…

There is a very small impact area, and yes, folks who use it, aware of co-pilot being involved :))

The thing is - I don't think I would dare to do that I've done without co-pilot in the first place. So it is a win anyway

Re: Did GitHub Copilot increase my productivity?

#323

Post by DrSiemer »

fzeroracer wrote: post #274
DrSiemer wrote: post #132

Earlier quoted context omitted.

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'.

Ah, so that's why all my code has become more concise and efficient and I've learned countless new tricks that I did not know before and probably would have never found without LLM's.

Too bad I'm "engaging with them wrong", I could have sworn it was helping me.

Seriously though, claiming LLM's don't have any higher level understanding of right and wrong and then extrapolating that to "they cannot possibly be used to improve things" is a very stubborn refusal of the fact that the most logical answer to the question "what can be improved here" is... actual improvements.

Re: Did GitHub Copilot increase my productivity?

#324

Post by zarathustreal »

munksbeer wrote: post #314
zarathustreal wrote: post #312

Earlier quoted context omitted.

My statement is clear and straightforward, I’m not sure how to put it any other way. LLM-generated tests don’t make sense as a concept because there are only roughly five properties you actually need to write tests for if you’re writing tests that actually provide any guarantees.

Apologies, but I understand the English words you're typing but I'm still not sure of the intent you're trying to convey to everyone. You're conversing in a very rigid style which isn't sympathetic to how people typically interact. I could just leave the discussion I guess, but in the interest of discourse, I don't find your statement meaningful because we're not all working in languages that I think you refer to. Ou…

Ah that makes sense to me, I see where I misunderstood you. When you say you don’t understand what you mean is that you do understand but you disagree with the point.

I’m on mobile so it’s hard to reference what I previously said but I’m assuming my statement needs to be weakened a bit to be correct. What I meant to say was that unit tests provide essentially no value because they can’t offer perfect guarantees, which is probably different than what I originally said. I’m assuming I just said “they offer no value” which is probably false in some cases for some people and some teams depending on their definition of value. My point was that unit tests do not make sense insofar as their purpose is to provide guarantees about the behavior of code because the information they provide does not meet the standard definition of “a guarantee”. For the above mentioned people/teams/situations/value definitions, they may make sense.

Hope that clarifies what I was trying to say.

Regarding languages, algebraic structures can be implemented in any Turing complete language. Likewise with property-based testing (with, eg randomized inputs across the domain). I’d be willing to guess it’s just a matter of education and/or desire keeping most developers from using it.

Re: Did GitHub Copilot increase my productivity?

#325

Post by shamano »

I guess it does when you use it parsimoniously.

Copilot helps me a lot when I have to write repetitive code, or when I have to change code slightly the same way in a lot of lines.

I never add large amounts of code at one go though, I think it would certainly add subtle bugs then.

Re: Did GitHub Copilot increase my productivity?

#326

Post by fzeroracer »

DrSiemer wrote: post #323
fzeroracer wrote: post #274

Earlier quoted context omitted.

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'.

Ah, so that's why all my code has become more concise and efficient and I've learned countless new tricks that I did not know before and probably would have never found without LLM's. Too bad I'm "engaging with them wrong", I could have sworn it was helping me. Seriously though, claiming LLM's don't have any higher level understanding of right and wrong and then extrapolating that to "they cannot possibly be used to…

They do not have any higher level understanding of right and wrong. You lead the model on by telling it to improve something, so it will rework the code in question and tell you that it's an improvement. Regardless or not if it is. Coding is about 70% subjective, 30% objective when it comes to figuring out improvements because the majority of improvements deal with business logic and things specific to your domain.
Post reply on HN