Ah, here it is; the Power Loom. And we're all weavers.
GitHub Copilot
491–500 of 1001 posts
Re: GitHub Copilot
#492I'm very enthusiastic about this kind of technology. I recently stopped using tabnine because the suggestions where often worse than the normal IDE completion while being on top of the list, but I do miss the magic.
I think AI in software development will save us a lot of time, so we can focus on more interesting things. It may replace a few humans in the long term, but as software developers we shouldn't be hypocrite because we work hard to replace humans by software.
Re: GitHub Copilot
#493This seems to work really well in cases where you're just laying down boilerplate. A few cherry-picked comments seem to suggest that React components are an ideal use case - which makes sense, that's a lot of munging and syntax to just render some strings.
However, I find the process of writing these sorts of functions cathartic and part of the process to get into zen-mode for coding. I think I'd feel less joy in programming if all of this was just done by glorified commenting and then code-review of the robot.
I like to think of coding in terms of athletic training, which usually is comprised of difficult tasks that are interspersed with lighter ones that keep you moving (but are giving you a bit of a break). Training for soccer teams often involved lots of sprinting and aerobic exercise - and in between those activities we would do some stretching or jogging to keep our body moving. These sorts of small functions (write a function to fetch a resource, parse an input payload, etc.) are when my brain is still moving but getting ready for the next difficult task.
Re: GitHub Copilot
#494Earlier quoted context omitted.
I mean you say this, but you and most likely the majority of programmers rely on dozens of repositories, packages and libraries with likely zero deep understanding of it (and at the very least haven't read the source code of ) so I don't really understand the difference here. The advantage of something like this is that instead of having to go to stack overflow or any number of reference sites and copy pasta it can j…
Importing an external, tested, reliable dependency is completely different from anonymous non-checked untested code in your repository committed by someone who did not even read it. Check out the memoize example. That fails as soon as you pass anything non-primitive but there’s no one documenting that.
anonymous non-checked untested code is problematic in all cases. This doesn't change that.
Re: GitHub Copilot
#495This looks amazing!
I was going sign up for the preview and stop immediately after reading the additional telemetry that is scrapped from my IDE, Microsoft would basically be allowed to steal my code and see it whenever they need. Including unintended snippets like local (git ignored) secrets and any sensitive information that it might catch without my "snippet by snippet" approval and not way to ignore files (afaik).
Until this is fixed, good luck but not thank you Microsoft.
Re: GitHub Copilot
#496I'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…
People have made some variation of this argument since the move from writing binary to writing assembly.
With every new layer of abstraction there’s more power.
The long term benefit of a tool that can do this well far exceeds what humans can do by hand, but that may not be true in the very short term.
Either way, I suspect the benefits to be big.
Re: GitHub Copilot
#497All your commits are belong to us
Re: GitHub Copilot
#498This looks awesome! And I'd really like to try it out.
2 security thoughts that I couldn't find answers to:
1. how does the input fed into OpenAI codex filter out malicious code pollution? or even benign but incorrect code pollution (relevant research on stackoverflow for example - https://stackoverflow.blog/2019/11/26/copying-code-from-stac...)
2. In an enterprise setting, what does the feedback loop look like? How do you secure internal code that is being fed back to the model? Does it use some localized model? HE, etc?
Re: GitHub Copilot
#499I'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…
Some people think the problem is that we don't have enough code. Anyone that has to maintain code knows that the problem is that we have too much code.
Re: GitHub Copilot
#500The gap between concept and working product is still very much in the human's wheelhouse. This is an accelerator to snippets not yet turned into a library and, in fact, a lot like a library in terms of it's day to day utility. This will not end or even change programming that much. The value I provide as a programmer is not about copying and pasting snippets. It's something totally separate different in kind from what copilot does. If it's helpful to do what I already do, sure I'll use it. But it ain't me, babe.