Articles

Benefits and Risks of Artificial Intelligence - Thomas G. Dietterich
https://medium.com/@tdietterich/benefits-and-risks-of-artificial-intelli...

Long-Term and Short-Term Challenges to Ensuring the Safety of AI Systems - J. Steinhardt
https://jsteinhardt.wordpress.com/2015/06/24/long-term-and-short-term-ch...

Ethical Issues in Advanced Artificial Intelligence - Nick Bostrom
https://nickbostrom.com/ethics/ai.html

Artificial Intelligence as a Positive and Negative Factor in Global Risk - Eliezer Yudkowsky 
http://intelligence.org/files/AIPosNegFactor.pdf

BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain - Tianyu Gu, Brendan Dolan-Gavitt, Siddharth Garg
https://arxiv.org/abs/1708.06733

Safely Interruptible Agents - Laurent Orseau, Stuart Armstrong
https://intelligence.org/files/Interruptibility.pdf

Concrete problems in AI safety
Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, Dan Mané
https://arxiv.org/abs/1606.06565

The Ethics of Artificial Intelligence - Nick Bostrom, Eliezer Yudkowsky
https://nickbostrom.com/ethics/artificial-intelligence.pdf

Research Priorities for Robust and Beneficial Artificial Intelligence - Stuart Russell, Daniel Dewey, Max Tegmark
https://futureoflife.org/data/documents/research_priorities.pdf

Books

Rationality: From AI to Zombies - Eliezer Yudkowsky 
https://intelligence.org/rationality-ai-zombies/

Superintelligence - Nick Bostrom
https://www.amazon.com/Superintelligence-Dangers-Strategies-Nick-Bostrom...

Smarter Than Us: The Rise of Machine Intelligence - Stuart Armstrong
https://intelligence.org/smarter-than-us/

The Internet of Us: Knowing More and Understanding Less in the Age of Big Data
http://books.wwnorton.com/books/The-Internet-of-Us/

The Machine Question: Critical Perspectives on AI, Robots and Ethics
http://machinequestion.org/