Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Aroma: Using machine learning for code recommendation

ai.facebook.com

Post reply on HN
Print view View original

11–20 of 62 posts

Re: Aroma: Using machine learning for code recommendation

#11

Post by spott »

I want something like this for math. Write an equation, or a definition and see a bunch of different 'versions' of that snippet and where they are being used.

This would help so much with understanding concepts and merging fields. It is way too common for different fields to independently "discover" some concept and be completely ignorant of all the work that has been done on that concept by some other field.

Re: Aroma: Using machine learning for code recommendation

#12

Post by franklsf »

bshipp wrote: post #10

Was anyone able to find a link to Aroma in that document? I found the colours made it very difficult to differentiate the links from the text and I couldn't find it. A quick search through Facebook's profile on Github turned up nothing.

There's a paper describing the approach in detail " rel="nofollow">https://arxiv.org/abs/1812.01158>, but Aroma itself is not open source yet.

Re: Aroma: Using machine learning for code recommendation

#15

Post by browsercoin2019 »

konamicode wrote: post #9

Seealso: IntelliCode for Visual Studio.

I also found for Code, https://visualstudio.microsoft.com/services/intellicode/

however when I try to install it on Mac OSX, I get

Couldn't find a compatible version of Visual Studio Intellicode - Preview with this version of Code

Re: Aroma: Using machine learning for code recommendation

#16

Post by franklsf »

mlthoughts2018 wrote: post #6
xpaulbettsx wrote: post #5

Earlier quoted context omitted.

> This is what makes Stack Overflow so helpful, the accompanying natural language description of intentionality or special cases, even if the code that is found isn’t precisely what’s needed, it demonstrates directionally what to do. You're entirely right, but if you're in an incredibly huge monorepo like Facebook, this information literally doesn't exist; that's part of the problem that Aroma is trying to solve - "h…

Wouldn’t it make more sense to spend the effort annotating these things? Or building models to provide the annotation? I mean, I work professionally in embedding models for computer vision and NLP, and my reaction to the article is that this seems like totally the wrong approach. You’re putting all this effort to create the embedding model out of the part that is both most superficial and least human interpretable (t…

Building models for natural language _and_ code for either NL/intent-based code search or automatically annotating code is indeed another hot research area!

I'd argue Aroma solves a different problem in that it surfaces more idiomatic patterns based on the code you already have. This also can be important especially in production environment, when you need to do things "the right way".

Re: Aroma: Using machine learning for code recommendation

#17

Post by mpolichette »

saagarjha wrote: post #13

One danger I can see coming up is that if someone writes incorrect code it could end up propagating throughout other codebases. I guess this is still an issue without automatic tools, but I feel like this might make it easier…

If you discover a better pattern, it might be easier to convert across the application if the same pattern is followed everywhere. So you might consider this a win.

Re: Aroma: Using machine learning for code recommendation

#18

Post by franklsf »

saagarjha wrote: post #13

One danger I can see coming up is that if someone writes incorrect code it could end up propagating throughout other codebases. I guess this is still an issue without automatic tools, but I feel like this might make it easier…

Aroma would only surface what it thinks is "idiomatic" coding patterns. So if you have many instances of incorrect code, you might already be in trouble :)
Post reply on HN