I’m a Ph.D student at MIT working in AI safety--mostly interpretability in deep networks. I thought I would very briefly share a list of links that I have bookmarked and go through every weekday. It usually takes me <15 minutes. Since I started doing this, I’ve been much more up to date and informed on current work. 

First is Twitter. For a long time, I resisted using Twitter because it’s terrible. But after I started following almost exclusively AI safety people and orgs, I’ve found a lot of good papers and ideas. 

Second, I check LessWrong and the AI Alignment Forum :) 

Finally, I look over new titles on arXiv for AI, ML, Computation and Language, and Computer Vision and Pattern Recognition. More often than not, I find a new paper that I want to click on and check out. 

And as a bonus, I’d of course also recommend these three newsletters.