Conversation

@bgcarlisle “We still don’t know in a very concrete way what these machine learning models are learning”

I had an interesting convo w/ Gerald Sussman where he said relevant things: http://dustycloud.org/blog/sussman-on-ai/

> "I'm not interested in that. I want software that's accountable." Accountable? "Yes, I want something that can express its symbolic reasoning. I want to it to tell me why it did the thing it did, what it thought was going to happen, and then what happened instead."