From what I read, it's doing search & clustering on AST based feature vectors. I'm a bit lost on the learning part, how does the system improve over time?
I’m guessing by learning the vectors over lots of ASTs?
Aroma: Using machine learning for code recommendation
51–60 of 62 posts
Re: Aroma: Using machine learning for code recommendation
#52Perhaps not as fancy, but I have been loving TabNine with Vim. (works with most editors) Its suggestions are scary good some of the time.
Re: Aroma: Using machine learning for code recommendation
#53I 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.
Checkout the work on homotopy type theory and proof assistants like Coq
Re: Aroma: Using machine learning for code recommendation
#54The most interesting (and I think difficult) approach here is properly representing the ASTs as vectors. There is a lot more possible when you get this right.
This. ML is so vector-y. And code is so graph-y. Can you point out some SOTA on bridging this ?
Try code2vec. It's pretty good.
Re: Aroma: Using machine learning for code recommendation
#55I wonder if anyone from Kite.com is reading this and if they have any comments?
Re: Aroma: Using machine learning for code recommendation
#56What is the IDE they are using ?
Re: Aroma: Using machine learning for code recommendation
#57What is the IDE they are using ?
I guess it's VS Code
Re: Aroma: Using machine learning for code recommendation
#58I 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.
It reminds me of Haskell's type based function search: https://hoogle.haskell.org/
Re: Aroma: Using machine learning for code recommendation
#59What is the IDE they are using ?
That's Atom with Nuclide.
Re: Aroma: Using machine learning for code recommendation
#60Maybe ontopic: I would like a voice controlled system that works with me. For example: saying, "I need a loop over a list" and promptly I get served in my text editor the loop. Or "I need to open a file and read contents". Or "Create an object ThisAndThat, with three properties" ... etc. Of course ideally would even ask for more details like, what kind of list is that, or how shall the file be read. How hard would be…
Well, I’ve been discussing it on HN for years now. There really hasn’t been much interest. https://news.ycombinator.com/item?id=8515987 https://news.ycombinator.com/item?id=11418285 Mention coding by voice and someone will explain how they can’t imagine not using a keyboard, or they bring up the open office problem. Considering the limited scope, it’s probably just a matter of the proper editor integration.
I think my idea goes about a rapid prototyping, where i build the skeleton of a program faster, no matter the boiler code, and then workout the details.
Intellisense or shortcuts do this up to a level, but the current big IDEs are limited. Maybe some editor with the concept of VIM with a separate command and edit mode would be more fit to work like that.