The point is: huuu-maans also produce bad code.
Sebb
wanton7
Where you able to quantify how much co-pilot helped your productivity? I expect you to have used it because you made this thread.
0
dimitarvp
Yes, humans also produce bad code. They can read, understand and correct it however, unlike ChatGPT and Copilot.
Very interested in you sharing your experience after you tell one of both: “please fix the bug in this code”. Would be super cool if they actually could, and if they can I’ll absolutely be integrating them in my workflow.
1
Sebb
Sure, it has to be a dialog.
Have you ever tried that with chatGPT?
It is not yet good enough (if only because there is no IDE-integration) to be usable, but we see where this is going.
0
dimitarvp
Who is “we”? 
Not to drag this sub-thread forever so I am stopping discussing the [supposed] quality of ChatGPT and Copilot after this comment – but somebody in the 1970s tried a few things with LISP, liked them a lot, and then 5000 articles later government and corps invested literal hundreds of billions on AI that never got created, leading to the so-called “AI winter”. Skynet never got created, too.
Tone the hype down. 
I’d love to be wrong btw. So far I see zero indications for it. We’ll see though.
3
Sebb
wanton7
Company I work for maybe year before corona pandemic hit had three backend programmers who used C# me included. We all tried using Visual Studio IntelliCode back then for 2 months. We three all agreed back then that it was actually hurting productivity. Of course that was many years ago and that AI product was very new back then. @dmitriid reply makes me believe these tools haven’t made much progress since then. Back then when we started using it there was lot of talk from Microsoft’s direction that it will greatly increase production. I’ve stopped believing these sale speeches because after using product myself it wasn’t at all good what they claimed it be. We all three programmers of course where senior programmers and our codebase used coding style we had decided on plus we used tools that automatically validates it. Example I started programming with C# in 2003.
0
dmitriid
They have really progressed since then, and I find especially IntelliJ tools quite useful (near-painless refactoring, finding duplicates, rewriting chunks of code to new standards etc.)
I’ve found Copilot to be a very minor improvement over the current state of the art in IDEs in those rare cases when it actually worked 
There’s probably an area where they could be somewhat of a leap eventually: boilerplate, data structure conversions etc. But they are not there yet.
===
Though I just remembered. We had a short straightforward bash script that we needed to convert to something windows-specific like BAT or PowerShell. ChatGPT produced garbage trying to convert it to BAT, and was only a small error away from a perfect conversion to PowerShell.
So code rewriting is maybe within the realm of possibility for some subset of code.
1
BartOtten
I do believe AI will eventually write a lot of code for developers. However, a few months ago I had a run with a few of them and quickly realised they are “not there yet”.
Although it is nice to see them write the License text including author name in the code…..ow wait…
2
KristerV
to reply to the original intent of OP: the only thing we can do is have more public projects with a permissive license on github. and since business isn’t going to change their codebase just to improve someone elses product (github) then there’s nothing to do.
i’m still waiting to have autocomplete that would just suggest me keys from a struct, lol otherwise the generators are helpful enough imo.
i just installed copilot anyway, just to try it out. i absolutely LOVE (the idea) that it can make a simple functions in Elixir (that would take me less than a minute anyway). i want to see how practical it proves to be. of course what it’ll be in 5 years is a whole other story.
1