This wasn’t made for programmers. It was made for middle management who think the reason the ticket is taking so long is because the devs can’t type more words per minute.
The other poster is either speaking from a place of ignorance, as they’ve never really used it, of they just aren’t smart enough to learn how to use a new tool.
As much as middle management sucks, devs blaming management for their own inability to learn is almost on the same level.
i mean i still think tab/auto completion is good to save time.
the problem is when people become reliant on it and just have it write entire chucks of code without going through it and checking it or changing it after the baseline is done.
You could say that about any kind of autocomplete. Why would people install snippet plugins into their vim/emacs? Sure you can just type everything by hand but it’s just more convenient.
Personally I find these kinds of inline AI suggestions make a more convincing use case than trying to prompt engineer a Chat based LLM and diverting your attention to phrasing specifics instead of the actual problem space.
Stuff like this is really useful when variable names are annoying, or when you have to repeat the same monotonous pattern over a large batch of code.
My favorite use of AI in code so far has been refactoring deprecated feature flags. “Replace enableXYZFeatureFlag with true and optimize the code”. Bam, 1-2 hours’ worth of crunch work solved in minutes.
If it takes 1+ hours of work to remove a feature flag branch in an area of code, I wouldn’t trust the correctness of anything the AI writes and would be super skeptical about anything the humans had written.
Can you please describe how you do this? I thought Github Copilot can only make changes to the currently open tab? It’s been a few months since I’ve used it, and I’ve only used the Visual Studio version, which I think isn’t as good as the Visual Studio Code version. Has Copilot already gotten to the point where you can tell it to make changes to an entire codebase?
I do go file by file, but I just copy and paste the same query into each. It also gives me a chance to do a quick review before moving on. It’s still a manual process but it’s a HELL of a lot faster than manually refactoring.
(I can’t give too many more details though since I use proprietary software that isn’t public facing)
Just…. Type it?
How lazy are we becoming?
This wasn’t made for programmers. It was made for middle management who think the reason the ticket is taking so long is because the devs can’t type more words per minute.
Guess I’m not a programmer, because this feature has been a real god-send in my recent projects.
The other poster is either speaking from a place of ignorance, as they’ve never really used it, of they just aren’t smart enough to learn how to use a new tool.
As much as middle management sucks, devs blaming management for their own inability to learn is almost on the same level.
i mean i still think tab/auto completion is good to save time.
the problem is when people become reliant on it and just have it write entire chucks of code without going through it and checking it or changing it after the baseline is done.
Then that wouldn’t exactly be a time saver, but rather time-consuming? Paradox
i mean finishing a variable declare with a tab is pretty convenient.
as is autocompleting an html5 structure.
Autocomplete is fine, but do we need “AI” to figure out left and right?
And I agree, chunks of code are bad.
You could say that about any kind of autocomplete. Why would people install snippet plugins into their vim/emacs? Sure you can just type everything by hand but it’s just more convenient.
Personally I find these kinds of inline AI suggestions make a more convincing use case than trying to prompt engineer a Chat based LLM and diverting your attention to phrasing specifics instead of the actual problem space.
Stuff like this is really useful when variable names are annoying, or when you have to repeat the same monotonous pattern over a large batch of code.
My favorite use of AI in code so far has been refactoring deprecated feature flags. “Replace enableXYZFeatureFlag with true and optimize the code”. Bam, 1-2 hours’ worth of crunch work solved in minutes.
If it takes 1+ hours of work to remove a feature flag branch in an area of code, I wouldn’t trust the correctness of anything the AI writes and would be super skeptical about anything the humans had written.
It takes a long time because it hits a lot of files, not because it’s logically complex. Also, that’s why unit and integration tests exist.
Can you please describe how you do this? I thought Github Copilot can only make changes to the currently open tab? It’s been a few months since I’ve used it, and I’ve only used the Visual Studio version, which I think isn’t as good as the Visual Studio Code version. Has Copilot already gotten to the point where you can tell it to make changes to an entire codebase?
I do go file by file, but I just copy and paste the same query into each. It also gives me a chance to do a quick review before moving on. It’s still a manual process but it’s a HELL of a lot faster than manually refactoring.
(I can’t give too many more details though since I use proprietary software that isn’t public facing)