Live data from Hacker News

GitHub Copilot is generally available

github.blog

491–500 of 796 posts

Re: GitHub Copilot is generally available

#491

I've been using Copilot for a few months and... Yeah, it makes mistakes, sometimes it shows you i.e. the most common way to do something, even if that way has a bug in it. Yes, sometimes it writes a complete blunder. And yes again, sometimes there are very subtle logical mistakes in the code it proposes. But overall? It's been *great*! Definitely worth the 10 bucks a month (especially with a developer salary). :inser…

> And sometimes, fairly rarely, but it happens, it's just surprising how good of a suggestion it can make.

I've had this experience too. Usually it's meh, but at one point it wrote an ENTIRE function by itself and it was correct. IT WAS CORRECT! And it wasn't some dumb boilerplate initialization either, it was actual logic with some loops. The context awareness with it is off the charts sometimes.

Regardless I find that while it's good for the generic python stuff I do in my free time, for the stuff I'm actually paid for? Basically useless since it's too niche. So not exactly worth the investment for me.

Re: GitHub Copilot is generally available

#492

Earlier quoted context omitted.

It's interesting to draw parallels between the way you describe it and the way more general large language models (LLMs, of which Copilot is in a sense, a specialized instance, applied to code, instead of general language) operate: they also always "know" how to answer any specific question, or how to complete any prompt, without any exception. A model which would be able to "show restraint", and "know when it doesn'…

There are language models that have an internal search engine, they can copy/verify the facts they generate from the source. They are also easier to update, just refresh the search engine. Now you have to provide a collection of "true facts".

Could you please link to some examples of such systems? Thanks in advance!

Re: GitHub Copilot is generally available

#493

Earlier quoted context omitted.

Worse yet, it's not available for the Orgs. So now each individual developer using it for work suddenly has to either pony up $10/month or figure out how to expense it.

I’m already terrified how many developers have been working on proprietary code bases with copilot, having an extension in their editor upload all their employer’s proprietary code to Microsoft, who then share it with OpenAI - then they’ve taken code OpenAI and Microsoft sent back to them, of unknown authorship, and added it into their code. And now those devs are going to have to go to their boss and explain all the…

Eh. I'd be okay with making all the software in the world open-source. It's only a matter of time before we have computers powerful enough to reverse-engineer everything in a split second anyway.

Re: GitHub Copilot is generally available

#494
post #199

Earlier quoted context omitted.

They intentionally opted in to sharing their work with you in a certain way. If someone copy pasted stack overflow answers and made them into a book, which they sold for money, that would be wrong.

People do do that. But I think that's a bit different because they add very little extra value. It doesn't take any effort. Why should I give them money? Copilot is different - it clearly takes a lot of skill and effort to turn a bunch of GitHub repos into a fancy autocomplete system.

it's using GPT-3 and, mhm, I guess everyone having proprietary access at GitHub's resources and computing power would be able to get this running.

Re: GitHub Copilot is generally available

#495
post #306
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…

> I've been using Copilot non-stop > I am honestly flabbergasted they think it's worth 10$/mo These two statments seem contradictory to me. Why are you using it 'non-stop' if it isn't even worth $10/month?

They gave it a fair shake, decided the price wouldn't be worth it. It's not inherently contradictory

I would consider it contradictory if they decided to continue using it while paying that price and unsatisfied

It's a trial run and the value isn't there for them

Re: GitHub Copilot is generally available

#496

Earlier quoted context omitted.

I think "SAAS fatigue" is a thing that needs to be considered. The SAAS model is great for startups and companies seeking recurring revenue. But the modern developer stack now involves dozens of companies gunning for a $5-10/month slice of the pie. In isolation, most developers could easily afford the $10/month for copilot. But most developers are probably using the free tier for half a dozen services. So the questio…

> modern developer stack now involves dozens of companies gunning for a $5-10/month slice of the pie. Can you name most useful ones? So far my only subscription is Idea. I'm considering to try Copilot as I've heard many good things about it.

Ngrok is a must have if you work with webhooks. Free tier is good but paid lets you have a fixed irl rather than having to update it daily.

Re: GitHub Copilot is generally available

#497
I'd pay for the service if the model was: I'll pay you when it's right and you refund me some amount every time copilot is wrong and I have to delete the entire block. It's good for small boilerplate stuff but that seems to be the limit. The attempts it makes are more complex code are really bad and I have to manually check it very closely to ensure it's right. I like the boilerplate boost but it's not worth $10/month to me.

Re: GitHub Copilot is generally available

#498

I've enjoyed using it for free, but not sure it's worth the $10/mo yet. When it works great, it's a nice-to-have for speeding up development but has yet to give me anything I wouldn't be able to just write myself. And when I wish it would give me the answer to something I don't know how to do, it spits out something very wrong. Also feels kind of icky to train on open source projects and then charge for the output.

> train on open source projects To be specific, the FAQ states: "It has been trained on natural language text and source code from publicly available sources, including code in public repositories on GitHub." Some have raised concerns that Copilot violates at least the spirit of many open source licenses, laundering otherwise unusable code by sprinkling magic AI dust... most likely leaving the Copilot user responsibl…

It’s hardly different from reading those projects yourself and learning from them.

Re: GitHub Copilot is generally available

#499
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…

Right on the money.

What I want is a copilot that finds errors ala spellcheck-esque. Did I miss an early return? For example in the code below

    def some_worker
        if disabled_via_feature_flag
             logger.info("skipping some_worker")
        some_potentially_hazardous_method_call()
Right after the logger call I missed a return. A copilot could easily catch this. Invert the relationship. I don't need some boilerplate generator, I need a nitpicker that's smarter than a linter. I'm the smart thinker with a biological brain that is inattentive at times. Why is the computer trying to code and leaving mistake catching to me? It's backwards.

Re: GitHub Copilot is generally available

#500

Earlier quoted context omitted.

> has yet to give me anything I wouldn't be able to just write myself Sure it has: Time. In terms of economics it's really simple: Does Copilot free up more than 10$ worth of your time per month? If the product works at all as I understand it (I haven't tried), the answer should be a resounding "yes, and then some" for pretty much any SE, given the current market rates. If the answer is no (for example because it pro…

Having used it quite a lot I'm not sure it does save me $10 of time per month. At least as often that it generates usefully correct code it generates correct appearing but actually totally wrong code that I have to carefully check and/or debug. It's quite nice not to have to type generic boilerplate in sometimes I guess but it's very frustrating when it generates junk.

I turned it off a week ago because I found it was wasting time when everything it generated required going back to fix issues.
Post reply on HN