Hacker News Reader

Comment by RodgerTheGreat | Hacker News Reader

Python's context-sensitive grammar makes it a particularly unsuitable target for text-based generation of code in this manner. If you continue with this project I expect you will find you get far better results from generating ASTs or choosing a language with a simple grammar in which most possible compositions of tokens are valid.

View on HN

Read the article, these type of algorithms have an easy time with syntax. The real issue is that the code produced is meaningless.

> The real issue is that the code produced is meaningless.

Sounds like something I'd code up.

Exactly, the difficulty is not really in producing valid code but meaningful code. Same with text generation - while a recurrent neural network might produce grammatically correct sentences, I don't think we're close to it producing an story with an actual plot, discernible characters etc.

What about a statically analyzable language? That could be factored into the loss function.

I was thinking the same. Not only that, if you would add multiple networks that, for example, weigh the possibility that a full line is "good" code, and another that evaluates a whole block (like google deep mind did with AlphaGo) so it looks like dense and complex code this could be a nice program trolling with pull requests on github :-D

So... some form of lisp would probably be best, right? Or maybe just binary or assembly?

Reply on news.ycombinator.com