Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Is GitHub Copilot a blessing, or a curse?

fast.ai

Post reply on HN
Print view View original

51–60 of 201 posts

Re: Is GitHub Copilot a blessing, or a curse?

#51

Post by seumars »

ALittleLight wrote: post #23

There's an interesting section that talks about what you want from a pair programmer - questioning your assumptions, spotting errors, debating design with you, etc, and how Copilot doesn't do this, but instead just spits out the code it thinks you want. That made me think that, when using Copilot, the human is actually the copilot. You're the one spotting bugs, picking different designs, and so on. I also think the d…

For what it’s worth, Copilot is not being marketed as anything else than code suggestion software - an alternative to google search, perhaps more of a “I’m feeling lucky” without having to actually type the search term. Knowing how to succinctly express a problem is half the problem after all.

Re: Is GitHub Copilot a blessing, or a curse?

#52

Post by skohan »

outsomnia wrote: post #39
skohan wrote: post #36

Earlier quoted context omitted.

Copilot is also almost certainly going to become better. For example, NVIDIA's DLSS was viewed as a failure at launch, but now it's almost magic in terms of offering better results at a lower performance cost.

Better at issuing haphazardly modified boilerplate that already exists... the real costs of writing code are about carefully choosing how pieces will fit together and deciding on minutae with that in mind. Copilot is the antithesis of designing good software.

AI is getting better than humans at a lot of complex task over time. Just because it can't code well now doesn't mean it won't in the future.

Re: Is GitHub Copilot a blessing, or a curse?

#53

Post by wonnage »

It's mentioned towards the end of the blogpost, but I think the real blessing in disguise might be the ability to identify similar code from elsewhere on Github and linking to it. Too many libraries have you wading through pages of documentation in search of a single usage example.

Some other ideas:

- Look for libraries with similar code and suggest them

- Deobfuscating minified variable names? Or just suggesting better ones for your source code

- Speculatively running things. If the model predicts importing a certain library, start indexing it before I even type it

- Estimate how long it thinks a block of code will take to write, based on the predicted code + past usage patterns (like the kindle reading progress estimate)

Just spitballing but all of these things feel more helpful and pair programming-y than trying to fabricate code out of the blue.

Re: Is GitHub Copilot a blessing, or a curse?

#54

Post by da39a3ee »

drpixie wrote: post #30

Now, imagine you're sitting with your boss, the average typically incompetent project manager or lead programmer ... Them: type type type ... accept accept ... save (unaware or choosing not to understand the meaningless uncompilable garbage that's been generated) Them: "There, that's the xxxx function. You'll have the rest done in 2 days, won't you!"

Agree with your sentiment. But there is a solution:

You: “Great, that might be good. Please stay here while we write and run the tests for that. (Our engineering handbook emphasizes how important tests are, as you know.)”

Re: Is GitHub Copilot a blessing, or a curse?

#55

Post by da39a3ee »

robertwt7 wrote: post #2

Feels like its a magical thing for me honestly. although I'm never waiting for suggestion while coding, sometimes the suggestions just slipped through and there is the OMG moment when it completes your thought. 1 thing though, tab for auto complete still does not work for me.. ever

Yeah tab didn’t work for me either. But then I turned off tab for autocomplete in settings and that seemed to fix it. I didn’t understand, but try it.

Re: Is GitHub Copilot a blessing, or a curse?

#57

Post by ALittleLight »

seumars wrote: post #51
ALittleLight wrote: post #23

There's an interesting section that talks about what you want from a pair programmer - questioning your assumptions, spotting errors, debating design with you, etc, and how Copilot doesn't do this, but instead just spits out the code it thinks you want. That made me think that, when using Copilot, the human is actually the copilot. You're the one spotting bugs, picking different designs, and so on. I also think the d…

For what it’s worth, Copilot is not being marketed as anything else than code suggestion software - an alternative to google search, perhaps more of a “I’m feeling lucky” without having to actually type the search term. Knowing how to succinctly express a problem is half the problem after all.

It's called "Copilot" and the tagline is "Your AI pair programmer." It's obviously being marketed as more than code suggestion software. It's being marketed as an AI pair programmer.

I agree that it is basically just code suggestion software, or like a big autocomplete. But it's definitely being marketed as more.

Re: Is GitHub Copilot a blessing, or a curse?

#58

Post by elevenoh »

croes wrote: post #13

It will depend on the companies and the price of Copilot. Then they will replace expensive experienced programmers with cheaper inexperienced ones and Copilot.

hmmm, remains to be seen!

might just keep the experienced/quality ones & have less need for a high quantity of inexperienced programmers.

Post reply on HN