Ethical guidelines for a superintelligence

By Ernest Davis. 2015

29 citations recorded by the source corpus.

Subfields: Astronomy and Astrophysics, Cognitive Neuroscience, Safety Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Astronomy and Astrophysics

1. Tom Everitt

In Cognitive Neuroscience

1. Marcus Hutter
2. Tom Everitt
3. Ben Goertzel

In Safety Research

1. Tom Everitt
2. Josivania Silva Farias
3. Carlos Denner dos Santos
4. Marcus Hutter
5. Patricia Vasconcelos Almeida
6. Iason Gabriel
7. Richard Ngo

Citations in the corpus

• Concrete Problems in AI Safety (2016, neutral): “A I] 2 1 Ju n”
• AGI Safety Literature Review (2018, background): “How do we get an AGI to work towards the right goals? MIRI calls this value specication. Bostrom (2014) discusses this problem at length, arguing that it is much harder than one might naively think. Davis (2015) criticizes Bostrom’s argument, and Bensinger (2015) defends Bostrom against Davis’ criti”
• Artificial Intelligence Regulation: A Meta-Framework for Formulation and Governance (2020, background): “Bestowing a sense of morality upon this superintelligence should be a priority, despite the difficulties associated with putting that into practice [9].”