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

21–30 of 326 posts

Re: Did GitHub Copilot increase my productivity?

#21

Post by noduerme »

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 think the nomenclature of calling generative AI an "AI" is just hype and that leads to disappointment. After all, it's much more exciting for investors than calling it the world's most expensive textual/audio/visual autocomplete. But that's really what this generatoon currently is.

And it can feel like magic, because we're pattern-seeking and pattern-matching creatures, so something that seems to intuit the pattern we're looking for (even if imperfectly) can feel quite a bit like reasoning with another human. To be a bit less generous to humans, it's often the same as talking with another human, because we spend much of our lives writing boilerplate or making small talk or otherwise just kind of on autopilot and answering patterns with expected responses without seriously engaging our complex reasoning. (Do you have to really think about how to map-filter-reduce a dataset anymore? Or think seriously about how you really are when someone says "how are you"? We don't usually expect other people to, and most of the time we're satisfied by exchanging recognizable / somewhat coherent language patterns which we can count on each other to fill in the gaps of. But this is not the intelligence in human intelligence).

The corporate hype machine works overtime to hype it as a solution, but that's just what they do. That's all spin. We see through it now, and we're getting to the point where people are asking the only important question about this tech, which is, how much will you pay for a nerfed autocomplete to do X?

Re: Did GitHub Copilot increase my productivity?

#22

Post by echelon »

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.

Re: Did GitHub Copilot increase my productivity?

#23

Post by matrix87 »

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 enterprise context. Are you confident in the result? Personally I'm too paranoid for that and I think more people should be

Re: Did GitHub Copilot increase my productivity?

#24

Post by toddmorey »

I don’t know if this is possible to reconfigure or turn off, but I HATE copilot guessing at file paths & file names (as I write an import for example). Usually I find the file reference broken because copilot hallucinated 3 directories.

Autocomplete for files & paths worked great before copilot got involved.

Re: Did GitHub Copilot increase my productivity?

#25

Post by noduerme »

aimazon wrote: post #16
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.

I don’t think you’re a dimwit but I read your post[1] with an example and I am curious to whether you feel you’re losing something by telling the LLM it’s wrong and to try again, rather than going through the exploratory/iterative learning process yourself. For example, would you have known to ask about GeoJSON if you had not come across and learned about it pre-LLM? More succinctly: do you feel you’re learning more…

You seem to be writing from a lost world when people enjoyed coding because they enjoyed learning new things with every project. I think that's sadly something only enjoyed at work by a very small minority these days.

Re: Did GitHub Copilot increase my productivity?

#26

Post by blibble »

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.

I wouldn't feel too bad, there's orders more magnitude more money put into this con vs. the last one (NFTs)

Re: Did GitHub Copilot increase my productivity?

#27

Post by anonzzzies »

azinman2 wrote: post #18
anonzzzies wrote: post #12

Earlier quoted context omitted.

It is incredible that you can replace 90% of upwork/fiverr/juniors(and many seniors for that matter) with a $20/mo tool for doing the most common work like api integrations and frontend work (both of which I find the most boring work outside the non programming like devops and, worse, fighting tools and versions because of useless updates). > It definitely hits a wall when I am working on something sufficiently esote…

I’d love to know the specifics on the ppl hiring the consultants and the work output. In my experience you need someone with experience to chain together any genAI output, as well as validate that it’s even correct. It’s not like it magically does everything for you.

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 we notice it is getting easier with the llms getting better. A year ago we still needed a human to evaluate even the basic scope of work, now llama3 + some tooling we built can automatically get us a locally generated report.

Re: Did GitHub Copilot increase my productivity?

#28

Post by frizlab »

fendy3002 wrote: post #15
jdlyga wrote: post #7

From my experience, Github Copilot is useful for its seamless autocompletes. But Github Copilot chat, a new feature, noticeably lags behind GPT-4. I get far better performance copying and pasting code into ChatGPT (GPT-4) than using Github Copilot. Both definitely help productivity, especially when generating code using an unfamiliar framework or library. It's great for generating skeleton code for small programs usi…

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.

Re: Did GitHub Copilot increase my productivity?

#29

Post by muglug »

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 coding velocity: https://arxiv.org/abs/2305.12050. In my own experience the time taken to review machine-generated suggestions often eats into developer time.

This is not a critique of LLMs in general — I’ve found ChatGPT really great for kicking off greenfield projects in well-known languages and frameworks.

Re: Did GitHub Copilot increase my productivity?

#30

Post by KaoruAoiShiho »

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.

It's shorter, you're working directly with the code base you're already thinking about, and it's plugged into it rather than having to start a new mental task when you're looking at a pull request.
Post reply on HN