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

GitHub Copilot

copilot.github.com

Post reply on HN
Print view View original

211–220 of 1001 posts

Re: GitHub Copilot

#211

Post by as300 »

mdellavo wrote: post #193
natfriedman wrote: post #60

Hi HN, we've been building GitHub Copilot together with the incredibly talented team at OpenAI for the last year, and we're so excited to be able to show it off today. Hundreds of developers are using it every day internally, and the most common reaction has been the head exploding emoji. If the technical preview goes well, we'll plan to scale this up as a paid product at some point in the future.

What do you think about this being overall detrimental to code quality as it allows people to just blindly accept completions without really understanding the generated code. Similar to copy-and-paste coding. The first example parse_expenses.py uses a float for currency - that seems to be a pretty big error that's being overlooked along with other minor issues around no error handling. I would say the quality of the…

Why would you say it's an error to use a float for currency? I would imagine it's better to use a float for calculations then round when you need to report a value rather than accumulate a bunch of rounding errors while doing computations.

Re: GitHub Copilot

#213

Post by rglover »

arrayjumper wrote: post #31
mdellavo wrote: post #8

Should I be impressed that the example parse_expenses.py on the home page doesnt include any error handling and uses a float for currency? This seems like it's going to revolutionize copy and paste programming.

It's a copilot. You're still the pilot. To be honest this seems like it can definitely save me a bunch of googling and let me stay in the ide.

Tell that to the new programmer who builds a piece of software using this creating an absolute mess.

The danger here isn't with experienced developers (this is, obviously, a tool with great potential for productivity). It's with people who just blindly trust what the robot spits out.

Once code like that is implemented in a mission-critical system without discernment, all hell will break loose.

Edit: worth watching this for context https://www.youtube.com/watch?v=ZSRHeXYDLko

Re: GitHub Copilot

#214

Post by mcintyre1994 »

onion2k wrote: post #182

GitHub Copilot may suggest old or deprecated uses of libraries and languages This raises two questions. - is there a way (right now or planned for the future) for library maintainers to mark suggestions to be removed from the suggestions? I can foresee Copilot being used as a source of 'truth' among less experienced developers, and getting people turning up in the Issues or Discord asking why the suggestion doesn't w…

I'd be pretty worried about this based on how many times an SO question has new better answers months/years later. I find that platform self-corrects reasonably well, with the newer better answer ending up at the top, but no idea how that'd happen here.

Re: GitHub Copilot

#215

Post by hit8run »

I tried the paid version of tabnine and was really unhappy because it suggested me code with syntax errors and introduced subtle bugs when I did not closely review every generated line. It was as if you have someone very impatient sitting next to you typing before actually really listening what you want to do. Is Copilot better? Does it suggest broken code, too?

Re: GitHub Copilot

#216

Post by mdellavo »

as300 wrote: post #211
mdellavo wrote: post #193

Earlier quoted context omitted.

What do you think about this being overall detrimental to code quality as it allows people to just blindly accept completions without really understanding the generated code. Similar to copy-and-paste coding. The first example parse_expenses.py uses a float for currency - that seems to be a pretty big error that's being overlooked along with other minor issues around no error handling. I would say the quality of the…

Why would you say it's an error to use a float for currency? I would imagine it's better to use a float for calculations then round when you need to report a value rather than accumulate a bunch of rounding errors while doing computations.

https://stackoverflow.com/questions/3730019/why-not-use-doub...

Re: GitHub Copilot

#217

Post by taneq »

kif wrote: post #132
natfriedman wrote: post #60

Hi HN, we've been building GitHub Copilot together with the incredibly talented team at OpenAI for the last year, and we're so excited to be able to show it off today. Hundreds of developers are using it every day internally, and the most common reaction has been the head exploding emoji. If the technical preview goes well, we'll plan to scale this up as a paid product at some point in the future.

I visited https://copilot.github.com/ , and I don't know how to feel. Obviously it's a nice achievement, not gonna lie. But I have a feeling it will end up causing more work. e.g. the `averageRuntimeInSeconds` example, I had to spend a bit of time to see if it was actually correct. It has to be, since it's on the front page, but then I realized I'd need to spend time reviewing the AI's code. It's cool as a toy, but I…

> I had to spend a bit of time to see if it was actually correct.

Interesting point - it reminds me of the idea that it’s harder to debug code than to write it. Is it also harder to interpret code you didn’t write than to write it?

Re: GitHub Copilot

#218

Post by crazygringo »

layla5alive wrote: post #181
crazygringo wrote: post #150

Earlier quoted context omitted.

> If you need to go through the suggested code to ensure it's correct, you may as well write it yourself? Not really. People are generally far faster at reading something and evaluating whether it's correct, than at writing something. In the same way it's faster to read a book than to write one. Not to mention the time it takes typing, fixing typos, etc. So this could genuinely be a huge timesaver if it helpful enoug…

I completely disagree with you. Reading code for correctness is difficult and not something most people do well at all. Reading code and reading for correctness are not the same, and most developers can write code a lot faster than they can verify it.

I guess we just disagree?

Honestly I don't even see how that's possible. Writing code, you're thinking about all the different ways to do it, eliminating the ones that won't work, evaluating the pros and cons of the ones that seem like they'll work, you start writing one and then realize it actually won't work, then start writing it a different way, try to decide what the best approach will be to make sure you're not committing an off-by-one error, and so on...

Whereas when you're reading code for correctness, you're just following the logic that's already there. If it works, it works. How could it possibly take longer than the whole creative process of coming up with it...?

Sure, maybe most people don't read code for correctness well. But then the code they write is surely even worse.

Re: GitHub Copilot

#219

Post by pjfin123 »

tomthe wrote: post #120
pjfin123 wrote: post #56

Earlier quoted context omitted.

I think this would fall under any reasonable definition of fair use. If I read GPL (or proprietary) code as a human I still own code that I later write. If copyright was enforced on the outputs of machine learning models based on all content they were trained on it would be incredibly stifling to innovation. Requiring obtaining legal access to data for training but full ownership of output seems like a sensible middl…

What if I put a licence on my Github-repositories that explicitly forbids the use of my code for machine-learning models?

Then the person training the models wouldn't be legally accessing your code.

Re: GitHub Copilot

#220

Post by dgb23 »

patwolf wrote: post #37

I wonder if there's any potential for Copilot to suggest malicious code because it's been trained on an open source projects containing intentionally malicious code.

Since it is per line I highly doubt it. I think of it as intellisense+. You select suggestions that you would have written anyway.
Post reply on HN