[williamtrask]

This article is meant for a policy audience, so that does keep the technical depth pretty thin. It's rooted in more rigorous deep learning work. Happy to send your way if interested.

[supermatt]

Posting info on that “rigorous deep learning work” here would be more beneficial to all than just sending to me.

[williamtrask]

I'm relatively close to publishing my PhD thesis which is broadly a survey paper of what you're describing. Will share (almost done with revisions).

[supermatt]

I look forward to the post.