Live data from Hacker News

GitHub Copilot is generally available

github.blog

511–520 of 796 posts

Re: GitHub Copilot is generally available

#511
Tabnine has been working in this space for more than 5 years and we would concur with much of the sentiment here on the importance of being able to adjust the length of the suggestions and ensuring the model is trained on ONLY fully permissive code.

TLDR: Tabnine advantages vs Copilot 1. Can run locally 2. As-you-type suggestions (mid-line) 3. Private model based on your code 4. Free plan available

Read more at https://tabnine.com/tabnine-vs-github-copilot

Re: GitHub Copilot is generally available

#512
I’m baffled by everyone questioning whether it’s worth $10/month.

I’m certain Copilot gives me more than a 2% productivity boost. That’s a conservative estimate (I wouldn’t be surprised if it’s more like 10-15%). If you consider 2% of what a developer makes each month, it comes to a lot more than $10. I’m not based in the US, but Levels.fyi suggests it’s not unusual for devs there to make $200K/year, that would mean $16.6K/month, 2% of which is $333. Maybe that’s a bit reductive, but the point is, $10/month is negligible if it gives you a noticeable productivity boost on a developer’s income.

And by the way, I don’t particularly love using Copilot. It can be annoying now I’m over the honeymoon period. But I think it’s pretty clear it speeds me up by a noticeable margin, and time is money.

Re: GitHub Copilot is generally available

#513
post #226

Earlier quoted context omitted.

"how to put a sentence together describing the rules, it absolutely doesn't actually understand how "Chii" melds work" The more experience I get with GPT-3 type technologies, the more I would never let them near my code. It wasn't an intent of the technology per se, but it has proved to be very good at producing superficially appealing output that can stand up not only to a quick scan, but to a moderately deep readin…

I wholeheartedly agree with your analysis, but feel like it’s ignoring the elephant in the room: writing code is not the bottleneck in need of optimization. Conceiving the solution is. Any time “saved” through Copilot and it’s ilk is immediately nullified by having to check it’s correctness. From there, the problem is worsened by the Frankensteinesque stitching together of disparate parts that you describe. I can’t i…

I also agree that I’d never assume copilot is right when it blurts out code, and that “writing code” is not the hard part — but I’d note three things I found from using copilot pretty intensively over the past year or so:

1. It has shifted some of the code-writing I do from generation to curation.

Most of the time, I have to make some small change to one of the first options I get. Sometimes I don’t. Sometimes I get some cool idiomatic way of doing something that’s still wrong, but inspires me to write something different than I originally planned. All of these are useful outcomes — and unrelated to whether someone is “actually thinking about what they’re writing”.

2. It has changed my tolerance for writing redundant code, for the better.

Like many programmers, I tend to optimize my code for readability first, and then other things later when I have more information. Sometimes, my desire for readability conflicts with my desire for code that avoids redundancy (e.g., “oh but if I put these three cases into an array I can just use a for loop and don’t have to write out as much code” etc. etc.) — and my old bias was avoiding redundancy more often than not. But copilot is really great at generating code that has redundancy, which has often helped me write more readable code in quite a few cases.

3. I refactor code way more now.

In part this is because, given code that already works but is not ideal (e.g., needs to be broken into more functions, or needs extra context, or some critical piece needs to be abstracted), copilot does a fantastic job at rewriting that code to fit new function prototypes or templates. IDEs can help with this task, for a few common types of refactoring, but copilot is way more flexible and I find myself much more willing to rewrite code because of it.

Copilot is not what many people want it to be, in much the same way that Tesla’s Autopilot is not what many people want it to be. But both do have their uses, and in general those uses fall into the category of “I, as human, get to watch and correct some things instead of having to generate all things.” This can be very useful. (FWIW, it takes some time to adapt to this; I teach and mentor a lot and I found myself relying on those skills a ton when working with copilot.)

We shouldn’t discount this usefulness just because these systems don’t also have other usefulness that we also want!

Re: GitHub Copilot is generally available

#515
post #226

Earlier quoted context omitted.

"how to put a sentence together describing the rules, it absolutely doesn't actually understand how "Chii" melds work" The more experience I get with GPT-3 type technologies, the more I would never let them near my code. It wasn't an intent of the technology per se, but it has proved to be very good at producing superficially appealing output that can stand up not only to a quick scan, but to a moderately deep readin…

I wholeheartedly agree with your analysis, but feel like it’s ignoring the elephant in the room: writing code is not the bottleneck in need of optimization. Conceiving the solution is. Any time “saved” through Copilot and it’s ilk is immediately nullified by having to check it’s correctness. From there, the problem is worsened by the Frankensteinesque stitching together of disparate parts that you describe. I can’t i…

Part of the pitch is that it helps you learn new languages, which I do sort of buy.

But yeah, the hard part of writing nontrivial software isn't typing code, it's the software architecture and design.

Re: GitHub Copilot is generally available

#516

I suspect they'd have more revenue if they priced it at $100/user/month. Right now, there is no competition, and an amateur developer will really benefit from copilot - certainly they will be more productive than a developer that demands just $1000 more annual salary.

Tabnine is a competitor! We have been doing this for 5+ years with more developers than Copilot. Please take a look at the posts and if curious visit https://www.tabnine.com/tabnine-vs-github-copilot

Re: GitHub Copilot is generally available

#517
post #195

I've been using Copilot non-stop on every hobby project I have ever since they've let me in (2021/07/13) and I am honestly flabbergasted they think it's worth 10$/mo. My experience using it till this day is the following: - It's an amazing all-rounder autocomplete for most boilerplate code. Generally anything that someone who's spent 5 minutes reading the code can do, Copilot can do just as well. - It's terrible if y…

+1. I've also been using it for hobby projects and have largely the same conclusions. I really do like that it spits out boilerplate for me, but when doing more than that, I still have to double-check all of it because as you said it does create incorrect, good looking output.

I can't justify $10 a month for it. Maybe as it improves.

EDIT: To clarify, $10 a month for personal use. We can't use it at work due to licensing, or it'd be worth that just to emit boilerplate.

Re: GitHub Copilot is generally available

#518
post #159

How does it compare with TabNine, now Copilot is not free anymore?

please take a look and also note that Tabnine while being more secure has also continued to evolve. We also have a free option that we have stood behind for 3+ years. https://www.tabnine.com/tabnine-vs-github-copilot

Re: GitHub Copilot is generally available

#519

I got like two weeks of the beta before they took it away from me today. I guess my small open-source project isn't prestigious enough to merit free access. Thanks I guess GitHub?

Come try Tabnine and if you need a custom model for your small OSS project please let me know.

Re: GitHub Copilot is generally available

#520
post #325

Earlier quoted context omitted.

Not OP - I use it non-stop for boiler plate filling as well. I wouldn't use it for anything other than that, so I would say it's worth honestly at max $1/month.

$1 is worth what, one minute of your time? If you're using a tool that doesn't even save you one minute, why bother?

What proportion of people are making $1 per minute?
Post reply on HN