Does this solve the right problem? Getting some code on the page has rarely been the expensive part of building something. Indeed, some long-ago experience with code generators suggests that making it easy to create code makes many problems worse down the line.
GitHub Copilot
381–390 of 1001 posts
Re: GitHub Copilot
#382I've been using the alpha for the past 2 weeks, and I'm blown away. Copilot guesses the exact code I want to write about one in ten times, and the rest of the time it suggests something rather good, or completely off. But when it guesses right, it feels like it's reading my mind. It's really like pair programming, even though I'm coding alone. I have a better understanding of my own code, and I tend to give better na…
Have you used any intelligent code completion in the past? E.g. I'd really be interested how it compares to TabNine[0], which already gives pretty amazing single line suggestions (haven't tried their experimental multi-line suggestions yet). [0]: https://www.tabnine.com
I've been using TabNine for a couple years – constantly impresses me, especially how quickly it picks up new patterns. I wouldn't say it's doing my job for me, but definitely saves me a lot of time.
Re: GitHub Copilot
#383I haven't kept up with the adversarial ML field recently, but I wonder how vulnerable these models are to adversarial attacks. - Could someone deliberately publish poor code to reduce the overall performance of the model? - Could someone target a specific use case or trigger word by publishing deliberately poor code under similar function definitions?
Also: what happens when a nontrivial portion of public code out there is ML-generated? How will it deal with feedback effects?
Re: GitHub Copilot
#384This technology should be available to everyone whose work contributed to it's development to use as they see fit. Free of Microsoft's tendrils.
The absolute gall of Microsoft claiming fair use to gate keep knowledge of millions of minds...
Re: GitHub Copilot
#385I'm amazed to see how positive the overall response is to this idea. Almost as if programmers think that writing programs is the worst part of the job and ready to be automated away.
As someone more aligned with the Dijkstra perspective, this seems to me like one of the single worst ideas I've ever seen in this domain.
We already have IDEs and other tools leading to an increase in boilerplate and the acceptance of it because they make it easier to manage. I can only imagine what kinds of codebases a product like this could lead to. Someone will produce 5000 lines of code in a day for a new feature, but only read 2000 of those lines. Folks that still expect you to only check in code you understand and can explain will become a minority.
I wonder how long it will be until someone sets up the rest of the feedback loop and starts putting up github projects made of nothing but code from this tool, and it can start to feed on itself.
Cargo-cult programming has always been a problem, but now we're explicitly building tools for it.
Re: GitHub Copilot
#386I can only imagine one of the big reasons to release Copilot to the public for free is to make it better by sending back to GitHub the "reviewed code". Example:
- Copilot suggests me a snippet of code
- It's almost what I wanted. I fix the code
- Copilot sends back the fixed code to GitHub
- Copilot gets better at guessing my (and others) wishes
Unless Copilot is running locally, I won't use it.
Re: GitHub Copilot
#387I've been using the alpha for the past 2 weeks, and I'm blown away. Copilot guesses the exact code I want to write about one in ten times, and the rest of the time it suggests something rather good, or completely off. But when it guesses right, it feels like it's reading my mind. It's really like pair programming, even though I'm coding alone. I have a better understanding of my own code, and I tend to give better na…
It could start to replace us in 20 years. Or reduce. It is exciting for now
Until it automatically knows when and how it's wrong, you'll still need a human to figure that out, and that human will need to actually know how to program, without the overgrown auto-complete.
May or may not reduce the demand for programmers, though. We'll see.
Re: GitHub Copilot
#388Doesn't look like it will be editor-agnostic which is a big shame. I've been using TabNine in Vim for a couple years, and I love it.
Re: GitHub Copilot
#389Calling it a pair programmer is a bit exaggeration though. How can it match a human?
Re: GitHub Copilot
#390I've been using the alpha for the past 2 weeks, and I'm blown away. Copilot guesses the exact code I want to write about one in ten times, and the rest of the time it suggests something rather good, or completely off. But when it guesses right, it feels like it's reading my mind. It's really like pair programming, even though I'm coding alone. I have a better understanding of my own code, and I tend to give better na…
Maybe it's just because humans are not as creative as they think. Whatever you do, thousands of others have done the same already. So no need to pay a high level programmer, just a mediocre one and the right AI assistant gives the same results.
> So no need to pay a high level programmer, just a mediocre one and the right AI assistant gives the same results.
I think of it as not needing juniors for boring work, all you need as a company is seniors and AI.