| Corrigibility N Soares, B Fallenstein, S Armstrong, E Yudkowsky Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015 | 131 | 2015 |
| Aligning superintelligence with human interests: A technical research agenda N Soares, B Fallenstein Machine Intelligence Research Institute (MIRI) technical report 8, 2014 | 111 | 2014 |
| The value learning problem N Soares Artificial intelligence safety and security, 89-97, 2018 | 109 | 2018 |
| Agent foundations for aligning machine intelligence with human interests: a technical research agenda N Soares, B Fallenstein The technological singularity: Managing the journey, 103-125, 2017 | 77 | 2017 |
| Logical induction S Garrabrant, T Benson-Tilsen, A Critch, N Soares, J Taylor arXiv preprint arXiv:1609.03543, 2016 | 48 | 2016 |
| Toward idealized decision theory N Soares, B Fallenstein arXiv preprint arXiv:1507.01986, 2015 | 39 | 2015 |
| Functional decision theory: A new theory of instrumental rationality E Yudkowsky, N Soares arXiv preprint arXiv:1710.05060, 2017 | 30 | 2017 |
| Problems of self-reference in self-improving space-time embedded intelligence B Fallenstein, N Soares International Conference on Artificial General Intelligence, 21-32, 2014 | 28 | 2014 |
| Formalizing convergent instrumental goals T Benson-Tilsen, N Soares Workshops at the Thirtieth AAAI Conference on Artificial Intelligence, 2016 | 22 | 2016 |
| Cheating death in damascus BA Levinstein, N Soares The Journal of Philosophy 117 (5), 237-266, 2020 | 18 | 2020 |
| Questions of reasoning under logical uncertainty N Soares, B Fallenstein Intelligence. org.-2015.-URL: https://intelligence. org/files …, 2014 | 18 | 2014 |
| Formalizing two problems of realistic world-models N Soares Intelligence. org.-2015.-URL: https://intelligence. org/files …, 2014 | 17 | 2014 |
| Vingean reflection: Reliable reasoning for self-improving agents B Fallenstein, N Soares Technical Report 2015-2, 2015 | 16 | 2015 |
| Cheating death in damascus N Soares, BA Levinstein Formal epistemology workshop (FEW) 2017, 2017 | 13 | 2017 |
| Asymptotic convergence in online learning with unbounded delays S Garrabrant, N Soares, J Taylor arXiv preprint arXiv:1604.05280, 2016 | 12 | 2016 |
| A formal approach to the problem of logical non-omniscience S Garrabrant, T Benson-Tilsen, A Critch, N Soares, J Taylor arXiv preprint arXiv:1707.08747, 2017 | 10 | 2017 |
| Aligning superintelligence with human interests: An annotated bibliography N Soares Intelligence 17 (4), 391-444, 2015 | 5 | 2015 |
| Inductive Coherence S Garrabrant, B Fallenstein, A Demski, N Soares arXiv preprint arXiv:1604.05288, 2016 | 3 | 2016 |
| Reflective variants of Solomonoff induction and AIXI B Fallenstein, N Soares, J Taylor International Conference on Artificial General Intelligence, 60-69, 2015 | 3 | 2015 |
| Tiling agents in causal graphs N Soares Tech. Rep. 2014–5, Machine Intelligence Research Institute, Berkeley, CA …, 2014 | 3 | 2014 |
