INFORMATION HAZARDS: A TYPOLOGY OF POTENTIAL HARMS FROM KNOWLEDGE
By Nick Bostrom. 2011
82 citations recorded by the source corpus.
Subfields: AI Ethics, Fairness & Society, Philosophy
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In AI Ethics, Fairness & Society
- Jess Whittlestone
- Aviv Ovadya
- Roman V Yampolskiy
- Stuart Armstrong
- William S. Isaac
- Iason Gabriel
- Borja Balle
- Nick Bostrom
In Philosophy
- Jess Whittlestone
- Aviv Ovadya
- Roman V Yampolskiy
- Stuart Armstrong
- Iason Gabriel
- Geoffrey Irving
- Nick Bostrom
- Zachary Kenton
Citations in the corpus
- Reducing malicious use of synthetic media research: Considerations and potential release practices for machine learning (2019, methodology): “(3)This is based loosely on a taxonomy from [14]”
- Taxonomy of Risks posed by Language Models (2022, background): “LM predictions that convey true information may give rise to information hazards, whereby the dissemination of private or sensitive information can cause harm [27].”
- Leakproofing the Singularity Artificial Intelligence Confinement Problem (2012, background): “Alternatively the AI can state that it has the power to cure all illness, feed the hungry and in general improve the human condition by a million fold (Chalmers, 2010).”
- The Vulnerable World Hypothesis (2019, unknown): “Bostrom (2011) discusses information hazards more generally.”
- Thinking Inside the Box: Controlling and Using an Oracle AI (2012, background): “But in either case, there are great social risks to asking certain types of questions (see Bostrom 2011 on the possible negative impact of certain types of knowledge).”