(2016-05-28) Sloan Writing With The Machine

Robin Sloan: Writing with the machine

As I’ve spent more time with rnn-writer, my opinion has — er — reinflated somewhat. I am just so compelled by the notion of a text editor that possesses a deep, nuanced model of… what? Everything ever written by you? By your favorite authors? Your nemesis? All staff writers at the New Yorker, present and past? Everyone on the internet? It’s provocative any way you slice it.

the code is now available, in two parts:

• torch-rnn-server is a server that runs the neural network, accepts snippets of text, and returns “completions” of that text. In truth, it’s just a couple of tiny shims laid beneath Justin Johnson’s indispensable torch-rnn project. (RNN, Neural Network)
• rnn-writer is a package for the Atom text editor that knows how to talk to torch-rnn-server and present its completions to the user*

Most of the energy in the deep learning scene is focused on what I’d call “generic” problems, the solutions to which are very broadly useful to a lot of people: