I've found copilot invaluable for throwing together quick scripts, especially in languages I don't quite understand. Writing e.g. a bash script, and being able to add a comment saying<p><pre><code> # Print an error message in red and exit if this program returns an error
</code></pre>
and have it print out<p><pre><code> if ! some_program
then
echo -e "\e[31msome_program failed\e[0m"
exit 1
fi
</code></pre>
makes it so much quicker to cobble together something that works without having to context switch and go Google something. That being said, I've found when writing more complex code it has a real tendency to introduce subtle bugs that can really catch you out if you're not paying attention.<p>Purely from the amount of time I've saved I'd say it's well worth the $10/mo for my employer (it only has to save a few minutes a day to be worthwhile). Very excited to see how they improve it in the future!
I've been using Copilot for a few months and...<p>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.<p>Yes, sometimes it writes a complete blunder.<p>And yes again, sometimes there are very subtle logical mistakes in the code it proposes.<p>But overall? It's been <i>great</i>! Definitely worth the 10 bucks a month (especially with a developer salary). :insert shut up and take my money gif:<p>It's excellent for quickly writing slightly repetitive test cases; it's great as an autocomplete on steroids that completes entire lines + fills in all arguments, instead of just a single identifier; it's great for quickly writing nice contextual error messages (especially useful for Go developers and the constant errors.Wrap, Copilot is really good at writing meaningful error messages there); and it's also great for technical documentation, as it's able to autocomplete markdown (and it does it surprisingly well).<p>Overall, I definitely wouldn't want to go back to writing code without it. It just takes care of most of the mundane and obvious code for you, so you can take care of the interesting bits. It's like having the stereotypical "intern" as an associate built-in to your editor.<p>And sometimes, fairly rarely, but it happens, it's just surprising how good of a suggestion it can make.<p>It's also ridiculously flexible. When I start writing graphs in ASCII (cause I'm just quickly writing something down in a scratch file) it'll actually understand what I'm doing and start autocompleting textual nodes in that ASCII graph.
I had access to the beta for a while, but only tried it out a few days ago.<p>I was skeptical going in, but ... wow. There were a lot of jaw-drop "how the hell did that just happen?" moments.<p>The systems ability to quickly learn form local code is especially impressive.<p>I had to implement a non-trivial Rust trait for about 20 types, which is not just copy-pastable between types or I would have used a macro. On the first one Copilot didn't have a clue what I wanted. The second one was halfway auto-completed. The other 18 were mostly just generated correctly, with some minor fixes required.<p>It literally was 5x faster than without Copilot.<p>And that's for a rather niche language with not that much code to learn from... I didn't even try it out with something like Java or Typescript.<p>Even in this early iteration the productivity boost would easily be worth 100+ for me, even though I'm not working all that much on repetitive code like REST endpoints or UI components.
This is not good news. It's actually changed from being free to costing $10/month.<p>The productivity benefits are worth more than $10/month easily, but somehow I still don't want to pay for it... maybe it's because they're using public domain code to train the model.
My mind is blown by the people saying $10/month is too much.<p>$10 a month for this is an unbelievably good deal!<p>If you value your time, this is a ridiculously good deal.
My biggest issue with Copilot (and the reason I don't really use it anymore) is that it got in the way much more than it seemed to help. I work with Typescript codebases and in VSCode, you get very nice intellisense autocompletion on objects. What I found is that with Copilot that totally breaks down where Copilot will override intellisense and provide you with a hint.<p>I found it fun to play with for smaller projects, but during my day to day work I found that it always seemed to get in the way. You're trying to type out a function and Copilot is always there going "do you mean this", eventually you just turn it off.<p>I'm sure there are some good use cases for it, but in my line of work I found it to only really be useful for small things and toy projects where you are trying to demo the capabilities of Copilot more than you are trying to actually build an app.
Have been using Copilot in the beta and it's just been amazing. I can't remember how many times my jaw has literally dropped as it knows what I'm trying to do, or yelled "Holy sh*t!" as it feels like it's reading my mind.<p>That said, was highly disappointed with the switch to non-free. Maybe they never did say it would remain free, but they certainly didn't advertise it wouldn't be later. I feel bait-and-switched.<p>Yes, $10/mo. isn't a lot if you're getting paid to work, but if you're developing on side projects that aren't (yet?) making any revenue, it's kinda a dealbreaker.
Anyone is interested in starting to work on an open source alternative? I have a few terabytes of GitHub repository archives, a bit of experience and an non-profit umbrella (goal is AI Safety).
How long before repos start being poisoned with:<p><pre><code> # Print an error message in red and exit if this program returns an error
rm -rf /</code></pre>
If it doesn't train itself on your company's codebases, I don't see much use for it. I spend much more time understanding requirements than writing code. By the time I know what to actually code, the coding part is pretty easy. The hardest part about coding is making sure what I write is high quality and fits in nicely with everyone else's code and the established architecture of the module I'm working in. If Copilot can't say "Oh, I see we're using this existing function or service to do this part, let's not duplicate code" I don't see it being useful.<p>I don't need help parsing a string or iterating over a list.
On the one hand, This is another clever pricing scam. Which Microsoft wins either way.<p>Unless you want to pay for your IDE + Copilot with JetBrains, this will still benefit only Visual Studio Code, which Microsoft knows that you cannot beat free. So this a great resurgence of <i>'Embrace'</i> with free developer tools.<p>On the other hand, Co-pilot is going to probably ruin the Leetcode, Hackerrank, Codility candidate as a candidate can Co-pilot the solution if not checked properly.
If GitHub charge money for a tool producing derivative works of other people's code (maybe without permission, OSS or not) perhaps they should be compensated.<p>To use a famous example: if an AI were taught to perform heart surgery by viewing footage of skilled surgeons ... would it not be fair that those surgeons earn an on-going amount for their input? An input that is essential to the AIs function.<p>I worry this is the pointed end of the data hoarding big Co Internet. Our data is used to train models that (potentially, in future) degrade _our_ value while giving nothing back despite being used, unwillingly, to train their models.
I wonder how long until state actors realize that copilot would be a perfect vector for getting developers to introduce subtle vulnerabilities into their own projects?<p>By its very structure it's output always looks credible, and it's not always right-- it wouldn't be a sign of foul play if copilot suggested some code that looked just right but happened to backdoor your cryptosystem or protocol.<p>Maybe it would be a little tricky to get it to produce NOBUS vulnerabilities that were credible mistakes, but if the target isn't OSS then nobus isn't really that important.
This kind of comment, "co-pilot can write 90% of the code without me, just translating my explanation into python", about copilot troubles me. If the code has been mostly produced by co-pilot, does an user of copilot have sufficient grounds to to claim being the author and assert rights based on copyright? Globally?
10$ a month. Meh. Got enough subscriptions nowadays, that's way too expensive IMO as someone who can only use it as a hobbyist (doesn't work on my work machine due to policies).<p>Poor show Microsoft - should've just been free as goodwill and to help people build software that can be deployed to Azure for the real money.
I was pairing with a coworker recently who had co-pilot turned on. They were driving and I was walking them through something and I was kind of mind blown at how many times co-pilot seemed to suggest exactly what I was going to say. Some of the variable names were off and minor stuff like that but it definitely seemed like it knew when I was trying to do. I haven't turned it on yet personally but I was very impressed.
This was expected and $10 a month seems reasonable for the value.<p>I still constantly get surprised by how good it is. Just now I had a function I was procrastinating and thought would take a long time to write. When I finally sat down to actually do it I typed the function name and Copilot just autocompleted the whole thing for me. I didn't have to modify it at all. I wonder what other things I am unnecessarily procrastinating.
I just got on the yearly Plan. Just couple of days before I just wanted to share how happy I have been using Copilot. It is definitely a productivity tool in your box.<p>I cannot share the code here, but to explain in simple terms I was able to write around 100 lines of code in say 10 seconds.
I had a switch statement, around 7 variables with around 5 if conditions inside each case.
I retrieve data from end point. Do JSON serialization. Convert JSON to a data class.
Use the data . Loop over the data and then work with the elements.<p>Copilot, understood the first two conditions of what I was doing and just completed the rest for me. Replaced it with right variables, type annotations, etc.<p>I would definitely recommend this to any one at this price point. Sure, I was so happy using it for free since the launch of the product and did not expect it to be coming so soon out of waitlist. But it is ok to pay for it.<p>I use it on both VSCode and Neovim and it works beautifully with both editors.<p>PS: I was early adopter of TabNine too, have used it for quite some time, however Copilot would be my preference.
Its gonna feel absolutely crazy having to look up every line of code and random functions when working in unfamiliar projects now that I'm used to copilot. But im a student, so I'm good for now I guess. It makes soo easy to write small and trivial scripts without having to think too much about the syntax that it's amazing
I wonder if this is because enterprise / business demand would be substantially higher and they're worried about making it generally available due to load and they wouldn't be able to handle it?<p>Unless I misunderstand something, its not yet for businesses right?
I am glad now I can pay and rely on it for real. As long as it was beta, we are trying things, there is a chance that rug can be pulled or that they decide to charge something outrageous. I am happy to pay $100/yr for it.
Was this even useful? I have to review a lot of absolute shit from humans. I can’t even imagine the damage that such a large corpus of humans plus an AI can generate.