We are going to set up a reading group in Madrid (Spain), focused on (semi-)technical papers from MIRI and others about AI safety. The goal is to gain a deeper understanding of current work in this area, and perhaps make some contributions in the future.

We have tentatively set our first meeting on Friday, September 21 afternoon at Campus Madrid, though the details may change. The first paper we will read is "Concrete Problems in AI Safety".

If you are interested in joining the group, please send me a message or leave a comment so we can gauge interest and arrange a new date if the current one does not suit you. The definitive date and venue will be published in the group page.

New to LessWrong?

New Comment