Hacker News Reader

Is this similar to Microsoft's IntelliCode? How does it differ?

This one is a character level language model. The Microsoft one is per token.

Btw, simple neural networks are far from doing the best for code. The kind of accuracy LSTM gives is already achieved with good n-gram models. E.g. see this one on a Linux code prediction: https://arxiv.org/pdf/1506.02078.pdf Also, there are other techniques that improve on top of the n-gram models: https://files.sri.inf.ethz.ch/website/papers/charmodel-iclr2...

I only skimmed the paper you linked, but I don't think it says what you say it says.

"We found that scaling up the model almost entirely eliminates errors in the n-gram category."

See table 1 in his last link.

What about gpt-2?