Corrigibility (2015) (with N. Soares, B. Fallenstein, and E. Yudkowsky) Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence. Posted on 16 December 201516 December 2015
Motivated Value Selection for Artificial Agents (2015) Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence. Posted on 16 December 201516 December 2015
How were predicting AIor failing to (2015) (with K. Sotala), Beyond Artificial Intelligence 11-29. Posted on 16 December 201516 December 2015
The errors, insights and lessons of famous AI predictionsand what they mean for the future (2014) (with K. Sotala and S. Ó hÉigeartaigh) Journal of Experimental & Theoretical Artificial Intelligence 26(3):317-342. Posted on 16 December 201516 December 2015
Risks and Mitigation Strategies for Oracle AI (2013) Philosophy and Theory of Artificial Intelligence, 335-347. Posted on 16 December 201516 December 2015
Risks and mitigation strategies for Oracle AI (2012) Philosophy and Theory of Artificial Intelligence 2011 Conference Proceedings. Posted on 16 December 201516 December 2015
Sandberg, A. (2014). Ethics of brain emulations. Journal of Experimental & Theoretical Artificial Intelligence, 26(3), 439-457. Posted on 16 December 201516 December 2015
Sandberg, A., (2015). Ethics of brain emulations. In Risk of General Artificial Intelligence, edited by Vincent Müller. Taylor & Francis 2015 (forthcoming). Posted on 16 December 201516 December 2015
Sandberg, A. (2013). Feasibility of whole brain emulation. In Müller, Vincent C. (ed.), Philosophy and Theory of Artificial Intelligence, (SAPERE, vol 5.), Berlin: Springer, pp. 251-264. Posted on 16 December 201516 December 2015
Artificial Intelligence, Times Educational Supplement, Interviewed by Madeleine Brettingham (1 February) Posted on 16 December 201516 December 2015