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

11–20 of 326 posts

Re: Did GitHub Copilot increase my productivity?

#11

Post by mhh__ »

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…

> spam

The first 100 lines of any project is spam (usually 0 entropy), so AI is a nice win.

Re: Did GitHub Copilot increase my productivity?

#12

Post by anonzzzies »

babyshake wrote: post #4

Writing fairly standard typescript APIs and React code, Copilot is immensely helpful and almost always correct. It definitely hits a wall when I am working on something sufficiently esoteric. As does ChatGPT, etc.

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 esoteric.

So do humans. Hiring humans to do that work well is hard and expensive, so it’s not strange that is harder for LLMs as well.

I am not sure that finding things LLMs are shite at makes them less productive for most things programmers are doing during the day, which is quite boring stuff. In my reality, which, before mid last year, had 100s of people (across clients I work with, not my company) doing integrations and frontend work, now fired most of these and focused more on optimising the pipeline for copilot, chatgpt and opus.

My friend who runs an outsourcing operation in India almost went out of business mid last year when he saw his EU clients cancelling all his contracts because his people could be replaced by openai; he pivoted by having his people use ai, do ai projects and becoming more (everyone already was that but it was more heavy on the coding) business analyst heavy. He fired no one and is doing better than before now, but he doesn’t hire ‘programmers’ anymore.

Re: Did GitHub Copilot increase my productivity?

#13

Post by anonzzzies »

simonw wrote: post #9
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…

Weird, because Copilot chat /is/ GPT-4 as far as I know. Or maybe they run it on 3.5?

They mix it to save on compute.

Re: Did GitHub Copilot increase my productivity?

#14

Post by simonw »

heethjain21 wrote: post #10
simonw wrote: post #9

Earlier quoted context omitted.

Weird, because Copilot chat /is/ GPT-4 as far as I know. Or maybe they run it on 3.5?

It runs both. Had seen this on the discussions on Github. https://github.com/community/community/discussions/58059#dis...

That original note about it using both 4 and 3.5 was from this comment on November 2nd: https://github.com/microsoft/vscode-copilot-release/issues/6...

GPT-4 Turbo - the much cheaper version of 4 - was announced on November 6th. So there's a good change they've switched to that at some point in the last 6 months.

Re: Did GitHub Copilot increase my productivity?

#15

Post by fendy3002 »

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

Re: Did GitHub Copilot increase my productivity?

#16

Post by aimazon »

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 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 or less or an equal amount when using LLMs?

[1] https://simonwillison.net/2024/Mar/22/claude-and-chatgpt-cas...

Re: Did GitHub Copilot increase my productivity?

#17

Post by anonzzzies »

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.

Nah, it seems a lot of people are using them wrong? OP seems to also fall in that category. I sit next to many people in pair programming situations and it’s quite weird to see very smart programmers using gpt or copilot; they are the ones shouting ‘stochastic parrot’ on forums and yet expect some kind of mind reading magic when using these tools. When I show that you can put a comment for your function, like you should do anyway, and it writes the function, it usually clicks. Many still find it ‘faster and easier’ to write the function themselves and that’s fine, but, like OP, doing things like entering ???? and generally expecting a useful result will not be optimal.

Re: Did GitHub Copilot increase my productivity?

#18

Post by azinman2 »

anonzzzies wrote: post #12
babyshake wrote: post #4

Writing fairly standard typescript APIs and React code, Copilot is immensely helpful and almost always correct. It definitely hits a wall when I am working on something sufficiently esoteric. As does ChatGPT, etc.

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.

Re: Did GitHub Copilot increase my productivity?

#19

Post by Barrin92 »

I used it for a few months and I think it made me less productive to be honest. I developed this strange "autocomplete disease" where I'd wait for autocomplete when I could've literally typed stuff out myself, it's like some weird tool dependent mental stutter.

And given that I've worked in the languages I write for a living, mostly C and Python for years it's not like it ever suggested anything I wouldn't have known how to write and especially in C it can produce some catastrophically shoddy code.

The one case where it's kind of nice is if you do a side project with a library that doesn't have good documentation and you don't know the API and it spits out some nice example, but honestly I don't consider that worth paying for.

Post reply on HN